© 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. 6934
    Prev
    Next
    INDEX
    Explanations

    lines that describe food items, particularly in relation to meal preparation and ingredients

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

    Lists of ingredients or components

    np_acts-logits-general · gemini-2.0-flash

    various kinds of items

    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
     الاطلاع
    -0.68
     perſon
    -0.68
    onActivityResult
    -0.67
    SuppressLint
    -0.66
    oplasts
    -0.66
    HandlerContext
    -0.66
     Daarom
    -0.65
    Портал
    -0.64
    Substances
    -0.64
     meriva
    -0.63
    POSITIVE LOGITS
     assorted
    0.85
     various
    0.71
    various
    0.68
     miscellaneous
    0.66
     sundry
    0.65
    各式
    0.64
     small
    0.62
    assorted
    0.60
     occasional
    0.58
    several
    0.58
    Activations Density 0.361%

    No Known Activations