© 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. 31-GEMMASCOPE-RES-16K
    11. 13398
    Prev
    Next
    INDEX
    Explanations

    references to scientific methods and experimental conditions

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

    scientific or academic text discussing experimental results, measurements, or technical analysis.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    words and phrases from technical academic and scientific writing.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.53
    ⤹
    -0.52
     Begins
    -0.50
    usammen
    -0.49
    ⚐
    -0.48
     nawr
    -0.48
     mijne
    -0.47
     dulces
    -0.47
    ientôt
    -0.46
    intios
    -0.46
    POSITIVE LOGITS
     ressources
    0.69
     utafitiHapana
    0.62
     whereof
    0.60
     (=
    0.58
     expli
    0.56
     „
    0.55
     nowadays
    0.54
     („
    0.54
     adresses
    0.52
     ressource
    0.52
    Activations Density 5.581%

    No Known Activations