© 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. 16-GEMMASCOPE-RES-16K
    11. 14701
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions, particularly involving parentheses and braces in equations

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

    Expressions containing parentheses

    np_acts-logits-general · gemini-2.0-flash

    function arguments or expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    geführt
    -0.50
     menant
    -0.46
    ################
    -0.46
    Aster
    -0.45
    Divider
    -0.45
     Down
    -0.45
    ʒ
    -0.44
     Das
    -0.44
     Aster
    -0.43
     Grant
    -0.43
    POSITIVE LOGITS
     surla
    0.85
    tvguidetime
    0.81
    Попис
    0.81
    Искәрмәләр
    0.76
     وتسجيلات
    0.76
    styleType
    0.75
    帖最后由
    0.75
     disambiguazione
    0.74
     <>",
    0.74
    ImageContext
    0.72
    Activations Density 0.758%

    No Known Activations