© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 2917
    Prev
    Next
    INDEX
    Explanations

    keywords related to software functionality and file management

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    instructional text explaining how to perform technical tasks or use software features.

    oai_token-act-pair · claude-4-5-haiku
    Triggered 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
    Negative Logits
     مشين
    -0.61
    UnitTesting
    -0.54
    MockMvc
    -0.48
    PhysRevLett
    -0.48
    expandindo
    -0.46
     referenties
    -0.46
     escuchado
    -0.45
    LoggerFactory
    -0.44
     getRole
    -0.43
     Exactos
    -0.42
    POSITIVE LOGITS
     Windows
    0.72
     settings
    0.71
     Settings
    0.70
     default
    0.69
     manually
    0.66
     automatically
    0.62
     users
    0.60
     workaround
    0.59
     user
    0.59
     Microsoft
    0.58
    Activations Density 0.755%

    No Known Activations