© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6960
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and medical conditions

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

    after capitalized words

    np_acts-logits-general · gemini-2.0-flash

    repaired boats

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ParallelGroup
    -0.59
    ContextHolder
    -0.56
     виправивши
    -0.56
    DoubleQuotes
    -0.55
    WithFormat
    -0.53
    createStatement
    -0.53
    lossians
    -0.51
     defStyleAttr
    -0.47
    馴染
    -0.47
    InstanceState
    -0.47
    POSITIVE LOGITS
     ulang
    0.82
     auffi
    0.65
     ולה
    0.65
     them
    0.63
     certaine
    0.62
    ThroughAttribute
    0.62
    σθαι
    0.61
     manualmente
    0.60
     את
    0.59
    ()/
    0.58
    Activations Density 0.984%

    No Known Activations