© 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-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 1078
    Prev
    Next
    INDEX
    Explanations

    references to survivor stories or mentions of survivors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -1.45
    AndEndTag
    -1.17
    HasForeignKey
    -1.13
     resourceCulture
    -1.10
    ]")]
    -1.08
     Efq
    -1.05
    awtextra
    -1.04
    createCanvas
    -1.03
     ExecuteAsync
    -1.02
    onViewCreated
    -1.01
    POSITIVE LOGITS
     [
    0.96
    [
    0.89
    ↵↵
    0.66
     {
    0.60
     auto
    0.58
     p
    0.57
    p
    0.56
    мп
    0.55
    g
    0.53
    <eos>
    0.53
    Activations Density 0.310%

    No Known Activations