© 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. 2520
    Prev
    Next
    INDEX
    Explanations

    programmatic structures and processes, particularly those related to subscriptions and configurations

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

    Code, schema, and query-related keywords

    np_acts-logits-general · gemini-2.0-flash

    programming contexts in Arabic

    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
    gany
    -0.54
    getRuntime
    -0.46
    rowth
    -0.41
     مُعرِّف
    -0.41
     ویکی‌پدیا
    -0.41
    quette
    -0.40
     resta
    -0.40
    走路
    -0.40
    ceedings
    -0.39
    REFERENCES
    -0.39
    POSITIVE LOGITS
    المناصب
    0.75
    HasForeignKey
    0.74
    MigrationBuilder
    0.72
    новниш
    0.67
     end
    0.67
     ***!
    0.65
    end
    0.63
     ExecuteAsync
    0.60
    ----</
    0.60
    End
    0.60
    Activations Density 0.076%

    No Known Activations