© 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. 31-GEMMASCOPE-RES-16K
    11. 4982
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematics and mathematical concepts

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

    mathematical and academic text containing references to journals, theorems, and technical documentation.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    entsch
    -0.35
    UES
    -0.31
     incentive
    -0.31
    řej
    -0.30
     Marg
    -0.30
    CardModule
    -0.30
    möglichen
    -0.30
    factor
    -0.29
     ніж
    -0.29
     Preston
    -0.29
    POSITIVE LOGITS
    MigrationBuilder
    0.66
    matical
    0.66
     TextAppearance
    0.63
     Mathematical
    0.63
     MATH
    0.63
    IntoConstraints
    0.63
    orianCalendar
    0.61
     math
    0.60
     数学
    0.60
    GenerationType
    0.60
    Activations Density 0.251%

    No Known Activations