© 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. 9-GEMMASCOPE-RES-16K
    11. 8259
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and symbols used in equations

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

    mathematical notation and technical symbols, especially subscripts and superscripts in formulas.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.34
    n
    -0.30
    -
    -0.30
    ,
    -0.28
    d
    -0.27
    <eos>
    -0.26
    x
    -0.26
    1
    -0.26
    2
    -0.25
    t
    -0.25
    POSITIVE LOGITS
     ujednoznacz
    0.90
    EndProject
    0.82
    WithIOException
    0.81
     メンテナ
    0.79
     MainAxisSize
    0.78
    IsContent
    0.77
    TintMode
    0.77
    𖧹
    0.77
     パンチラ
    0.75
    IVEREF
    0.75
    Activations Density 4.765%

    No Known Activations