© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 11457
    Prev
    Next
    INDEX
    Explanations

    symbols and separators in data or text, particularly representing mathematical and scientific notations

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

    Text containing special characters

    np_acts-logits-general · gemini-2.0-flash

    chemical formulas and ratios

    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
    ,
    -0.91
    -
    -0.83
    ’
    -0.78
     in
    -0.74
     and
    -0.70
     
    -0.70
    :
    -0.70
    .
    -0.69
    as
    -0.67
    an
    -0.67
    POSITIVE LOGITS
    tvguidetime
    1.38
    LookAnd
    1.30
     يتيمه
    1.23
     ModelExpression
    1.21
     myſelf
    1.20
     Efq
    1.20
    RegressionTest
    1.19
    parsedMessage
    1.18
    sizeCache
    1.18
     JpaRepository
    1.17
    Activations Density 0.009%

    No Known Activations