© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6661
    Prev
    Next
    INDEX
    Explanations

    references to judicial cases and their outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    legal and academic citations or references.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    mentions of multiplicity or repetition—plural count nouns and frequency/quantity terms indicating multiple instances or repeated events.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    phrases indicating frequency or recurrence, particularly in formal or legal contexts (such as "several times," "several occasions," "several cases," and similar constructions).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.63
    saraba
    -0.61
    contentLoaded
    -0.60
    aarrggbb
    -0.58
    tagHelperRunner
    -0.57
     Италијани
    -0.57
    цездатний
    -0.54
    modelBuilder
    -0.54
    Билгалдахарш
    -0.52
    EDEFAULT
    -0.52
    POSITIVE LOGITS
     including
    0.52
     Including
    0.48
    including
    0.47
    Including
    0.43
     fotográfico
    0.41
     reciclado
    0.41
     incluyendo
    0.40
     incluido
    0.40
     flera
    0.40
     successively
    0.40
    Activations Density 0.582%

    No Known Activations