© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4262
    Prev
    Next
    INDEX
    Explanations

    phrases indicating purpose or intent

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

    words or phrases that introduce explanations, instructions, or consequential actions (particularly "para" meaning "for/in order to" and "Pour" meaning "for").

    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
     Italij
    -0.46
     Administração
    -0.45
     Capacidad
    -0.44
     emprego
    -0.43
     Matériau
    -0.43
     ganchillo
    -0.43
     Divulgação
    -0.42
     nacionalidad
    -0.42
     Utilisez
    -0.42
     Jerusalén
    -0.42
    POSITIVE LOGITS
    SequentialGroup
    0.62
    DockStyle
    0.59
    waitKey
    0.56
    migrationBuilder
    0.55
    ErrUnexpectedEOF
    0.54
     subsist
    0.53
     يتيمه
    0.52
     defaultstate
    0.52
     <<<<<<<<<<<<<<
    0.50
    WriteTagHelper
    0.50
    Activations Density 0.056%

    No Known Activations