Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12780
    Prev
    Next
    INDEX
    Explanations

    symbols and syntax related to coding and programming structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    Regressor
    -0.38
    ArgumentParser
    -0.36
    RuleContext
    -0.36
    Packs
    -0.35
     rule
    -0.35
     regole
    -0.35
    İŞ
    -0.34
     smaak
    -0.34
     permeability
    -0.34
    Pack
    -0.33
    POSITIVE LOGITS
    __*/
    0.71
     *>(
    0.56
     snippetHide
    0.55
    BeginInit
    0.54
    WriteTagHelper
    0.53
     Chwiliwch
    0.53
    OGND
    0.53
    GIVEREF
    0.53
    posedge
    0.52
    LabelTagHelper
    0.51
    Activations Density 0.106%

    No Known Activations