© 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. 8219
    Prev
    Next
    INDEX
    Explanations

    numbers and statistical measurements related to data collection and analysis

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

    descriptions of quantities or counts—especially “number of” metrics, data sizes, or rates—indicating how many items are returned, processed, stored, or engaged in technical contexts.

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

    Technical or scientific text describing quantities, measurements, or data processing operations, particularly focusing on phrases that specify amounts, counts, or capacities being measured, stored, or manipulated.

    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
     very
    -0.54
     figliu
    -0.50
     mahdol
    -0.46
     abbond
    -0.43
     dezelve
    -0.43
     appunto
    -0.43
     eenig
    -0.41
     muy
    -0.41
    atissimo
    -0.41
    cshtml
    -0.40
    POSITIVE LOGITS
    MessageOf
    0.61
    хьтан
    0.53
    Personensuche
    0.53
     Taktlose
    0.50
    
    0.48
    tagHelperRunner
    0.47
    WithIOException
    0.45
     fewest
    0.44
     Autorisations
    0.43
    Bakgrunnsstoff
    0.41
    Activations Density 0.601%

    No Known Activations