© 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. 634
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to specific syndromes and conditions

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

    terms associated with mental health or psychological conditions

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

    omni, pana, carni, gyne, riac/iac/asis

    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
    ELTS
    -0.55
     continúas
    -0.54
    }")
    -0.53
    eliner
    -0.53
    SerializedSize
    -0.51
    aarrggbb
    -0.50
     panahon
    -0.48
     متعلقه
    -0.48
     protoimpl
    -0.48
     Xunit
    -0.48
    POSITIVE LOGITS
     FetchType
    0.59
    celia
    0.58
    iac
    0.56
    riac
    0.55
     keper
    0.53
    astic
    0.53
    èque
    0.52
    asty
    0.52
    saraba
    0.51
    stanbul
    0.51
    Activations Density 0.143%

    No Known Activations