© 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-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 10889
    Prev
    Next
    INDEX
    Explanations

    quantitative descriptors and terms indicating amounts or counts

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

    Quantifiers like "few," "many," "any," or "more"

    np_acts-logits-general · gemini-2.0-flash

    quantity pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.66
    ArrowToggle
    -0.58
    ategy
    -0.58
     nahilalakip
    -0.56
    endcsname
    -0.54
    ConstraintMaker
    -0.54
    WEBPACK
    -0.54
    ringa
    -0.53
    hlers
    -0.53
     AssemblyVersion
    -0.52
    POSITIVE LOGITS
     ones
    1.16
     davon
    0.74
     others
    0.72
     deles
    0.71
    jenige
    0.70
     daarvan
    0.65
    Others
    0.63
     thereof
    0.62
    jenigen
    0.61
     vôtre
    0.60
    Activations Density 0.588%

    No Known Activations