© 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. 580
    Prev
    Next
    INDEX
    Explanations

    instances of metadata or document structure indicators

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

    the beginning of sections or segments in a document, marked by special tokens

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

    names and titles

    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
     houſe
    -0.71
     Efq
    -0.69
     ſever
    -0.66
     uſed
    -0.66
     HasFactory
    -0.66
     ſte
    -0.65
     Eury
    -0.65
     Maryam
    -0.64
     Uff
    -0.64
     uncin
    -0.64
    POSITIVE LOGITS
     NSCoder
    0.77
    <%=
    0.72
     विश्वसनीयता
    0.70
     Réponses
    0.70
     EconPapers
    0.64
    calaure
    0.62
    دانشنامهٔ
    0.61
    protoimpl
    0.59
     noqa
    0.58
    Precalculus
    0.58
    Activations Density 0.060%

    No Known Activations