© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12538
    Prev
    Next
    INDEX
    Explanations

    references to specific scientific terminologies and parameters

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

    The letter "E" in various contexts (formulas, grade letters, scientific notation, variable names).

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.63
     unterkunft
    -0.57
    مصادر
    -0.56
    subpackage
    -0.56
    rrggbb
    -0.54
    GrantedAuthority
    -0.54
    wikidata
    -0.54
     AssemblyCulture
    -0.52
     zainteres
    -0.52
    ambilan
    -0.52
    POSITIVE LOGITS
    E
    0.80
     E
    0.78
     e
    0.70
    EIF
    0.68
    e
    0.66
     EoL
    0.63
    ejs
    0.63
     EIF
    0.62
    EGL
    0.60
     El
    0.59
    Activations Density 0.857%

    No Known Activations