© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 53746
    Prev
    Next
    INDEX
    Explanations

    references to materials or items described as "bead."

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

    bead assays and separation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     arşivlendi
    -0.71
     nahilalakip
    -0.61
    '))
    -0.59
    }{*}{
    -0.58
    .";
    -0.58
    !")
    -0.58
    BufferException
    -0.57
    `;
    -0.56
     betweenstory
    -0.56
     indisponible
    -0.56
    POSITIVE LOGITS
     bead
    2.30
     Bead
    2.17
     beads
    2.16
    Bead
    2.14
     Beads
    2.11
    bead
    2.06
    beads
    1.74
     beaded
    1.63
     perles
    1.02
    珠
    0.85
    Activations Density 0.003%

    No Known Activations