© 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-2-2B
    7. Residual Stream - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 1998
    Prev
    Next
    INDEX
    Explanations

    mentions of legal exhibits or evidence in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vation
    -0.81
    </td>
    -0.80
    °)
    -0.76
    zaki
    -0.75
    cination
    -0.74
    e
    -0.73
    ərbaycan
    -0.72
    neux
    -0.72
    }-{
    -0.71
    lementary
    -0.71
    POSITIVE LOGITS
     avoient
    1.05
    ьаж
    1.01
     étoient
    1.00
     réforme
    1.00
     auroit
    0.98
     étoit
    0.96
     quæ
    0.95
     pouvoit
    0.95
    Exhibit
    0.94
     تانيه
    0.92
    Activations Density 0.025%

    No Known Activations