© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11512
    Prev
    Next
    INDEX
    Explanations

    references to literature or notable achievements within the literary context.

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

    content related to works of literature, awards, and technical subjects like coding.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    the word "final" or phrases containing "final", especially in titles or names of works.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    Follows "final"

    np_acts-logits-general · gemini-2.0-flash

    final analysis, step, order, thing

    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
     Groves
    -0.58
     HasFactory
    -0.57
    лтамалар
    -0.55
    *}{
    -0.54
    ItemBackground
    -0.53
    жом
    -0.52
    })*/
    -0.52
    bilirsiniz
    -0.52
    toHaveBeenCalled
    -0.51
    CK
    -0.51
    POSITIVE LOGITS
    RenderAtEndOf
    0.95
    ArgsConstructor
    0.78
     FINAL
    0.76
     Verdict
    0.73
     destination
    0.72
     كومونز
    0.71
    StoryboardSegue
    0.69
    ScopeManager
    0.69
    Final
    0.68
     Final
    0.68
    Activations Density 0.100%

    No Known Activations