© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1538
    Prev
    Next
    INDEX
    Explanations

    the presence of legal terminology or concepts associated with court procedures

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

    the beginning of structured code or script blocks

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

    XML or configuration attributes

    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
    Portale
    -0.95
    archiviato
    -0.72
     MotionEvent
    -0.66
    ậc
    -0.63
    Gweler
    -0.61
     विश्वसनीयता
    -0.59
     faſt
    -0.57
    enumi
    -0.57
    성
    -0.57
     onAnimation
    -0.56
    POSITIVE LOGITS
    Sqft
    2.13
     initComponents
    0.58
    amazonaws
    0.55
     autorytatywna
    0.55
    BeginInit
    0.53
     internetowa
    0.46
    quelles
    0.46
    jectures
    0.46
    Distances
    0.44
     devons
    0.44
    Activations Density 0.008%

    No Known Activations