© 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. 639
    Prev
    Next
    INDEX
    Explanations

    sections that indicate the beginning of new topics or paragraphs

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

    the beginning of a new sentence or paragraph

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

    is the

    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
     tartalomajánló
    -0.79
    Carriera
    -0.58
     cad
    -0.53
     mud
    -0.53
    ाषा
    -0.51
    ++){
    -0.51
     déta
    -0.50
    hort
    -0.50
    npos
    -0.49
    imba
    -0.49
    POSITIVE LOGITS
    GraphicsUnit
    4.55
    tvguidetime
    1.05
    CloseOperation
    0.91
    SuppressLint
    0.88
     doInBackground
    0.87
     HasFactory
    0.82
     getItemId
    0.78
     оригіналу
    0.76
     MessageBoxIcon
    0.75
     GoogleFonts
    0.74
    Activations Density 0.003%

    No Known Activations