© 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. 2863
    Prev
    Next
    INDEX
    Explanations

    method calls or function settings related to parameters or contexts in programming code

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

    programming methods/functions involving setting parameters or values.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
     Silverman
    -0.51
     indexOf
    -0.50
     Kraw
    -0.49
    Portály
    -0.49
     onClose
    -0.49
     irreparable
    -0.48
     randomNumber
    -0.47
     Jakob
    -0.47
    fromCharCode
    -0.47
     Kraus
    -0.47
    POSITIVE LOGITS
    set
    0.96
     set
    0.94
    Set
    0.85
     Set
    0.85
     SET
    0.69
     purpoſe
    0.65
    SET
    0.60
    TypedDataSet
    0.60
     ſet
    0.58
     Sets
    0.58
    Activations Density 0.090%

    No Known Activations