© 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. 25-GEMMASCOPE-RES-16K
    11. 14990
    Prev
    Next
    INDEX
    Explanations

    code structure elements such as method definitions and access modifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/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.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MainAxisSize
    -0.69
     queſta
    -0.65
    ConstraintMaker
    -0.63
     calendriers
    -0.62
    enterOuterAlt
    -0.62
    Xna
    -0.62
     للاسماء
    -0.62
    featureID
    -0.59
     autorytatywna
    -0.59
     ModelRenderer
    -0.59
    POSITIVE LOGITS
    <eos>
    0.46
    ↵
    0.36
     manis
    0.31
     Agreement
    0.31
     help
    0.30
    </u>
    0.30
    rement
    0.30
     horen
    0.29
    structure
    0.29
    失
    0.29
    Activations Density 0.056%

    No Known Activations