© 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. 18-GEMMASCOPE-RES-16K
    11. 876
    Prev
    Next
    INDEX
    Explanations

    instances of medical diagnostics or assessments indicating negative results

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

    Code, dates, and math symbols

    np_acts-logits-general · gemini-2.0-flash

    dates and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interopRequire
    -0.55
    CppMethod
    -0.54
    CppCodeGen
    -0.54
     nakalista
    -0.52
     Ladd
    -0.52
    をの
    -0.51
    Pyx
    -0.51
    Secondly
    -0.49
    Бахар
    -0.48
    amerikanischer
    -0.48
    POSITIVE LOGITS
    ftagPool
    0.77
    TagMode
    0.57
     يتيمه
    0.53
    MigrationBuilder
    0.53
    例文帳に追加
    0.50
     invitar
    0.49
    SaveChangesAsync
    0.49
    $_['
    0.48
    GEBURTSDATUM
    0.47
    Personensuche
    0.47
    Activations Density 0.006%

    No Known Activations