© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1365
    Prev
    Next
    INDEX
    Explanations

    references to formal studies, data collection methods, and participant details in research contexts

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

    specific phrases related to legal documentation or formal complaints

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

    health concepts and requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    .
    -0.86
    ↵
    -0.77
    ,
    -0.75
     (
    -0.64
    ?
    -0.64
    (
    -0.64
     -
    -0.64
    <strong>
    -0.63
    ↵↵
    -0.60
    :
    -0.60
    POSITIVE LOGITS
     дописавши
    1.47
     autorytatywna
    1.45
     propOrder
    1.35
     للمعارف
    1.33
     فريبيس
    1.32
    Autoritní
    1.30
    AndEndTag
    1.28
    ConstraintMaker
    1.27
    =$?
    1.26
    帖最后由
    1.26
    Activations Density 0.575%

    No Known Activations