© 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. 22-GEMMASCOPE-RES-16K
    11. 10605
    Prev
    Next
    INDEX
    Explanations

    mathematical and statistical terms or symbols in the context of research data

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

    Prepositions followed by comparatives

    np_acts-logits-general · gemini-2.0-flash

    percentages and comparatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.82
     مشين
    -0.77
    存于互联网档案馆
    -0.73
     Савезне
    -0.70
     referrerpolicy
    -0.68
     useStyles
    -0.67
     isNameExpr
    -0.64
    <?
    -0.64
     ویکی‌پدیای
    -0.63
     كومونز
    -0.63
    POSITIVE LOGITS
     
    2.15
     $
    0.54
     ২
    0.44
    ktır
    0.43
    ()]);
    0.42
    acakt
    0.41
     ১
    0.40
    wikk
    0.39
    ]');
    0.39
     fous
    0.39
    Activations Density 2.925%

    No Known Activations