© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 13109
    Prev
    Next
    INDEX
    Explanations

    complex mathematical notations or expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    teness
    -0.48
     rangs
    -0.47
     než
    -0.46
    ยัง
    -0.46
     urmă
    -0.45
     rigue
    -0.44
    begin
    -0.44
    select
    -0.44
    বহ
    -0.43
    был
    -0.43
    POSITIVE LOGITS
     doInBackground
    0.95
    ChildScrollView
    0.86
    gages
    0.75
    帖最后由
    0.72
    Personendaten
    0.72
    ViewFeatures
    0.72
     jLabel
    0.71
    ⓧ
    0.69
    раздо
    0.69
    ">{{$
    0.69
    Activations Density 0.145%

    No Known Activations