© 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. 7-GEMMASCOPE-RES-16K
    11. 12572
    Prev
    Next
    INDEX
    Explanations

    references to prior discussions or mentions in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GenerationType
    -0.49
    ArgsConstructor
    -0.41
    ंदीखरीदारी
    -0.40
    
    -0.38
    complexContent
    -0.38
    Kra
    -0.38
    STI
    -0.37
    のおかげ
    -0.37
     Paglinawan
    -0.37
     Kra
    -0.36
    POSITIVE LOGITS
     previously
    0.91
     Previously
    0.82
     eerder
    0.81
    เคย
    0.79
    Previously
    0.79
    previously
    0.77
     zuvor
    0.72
     wcześniej
    0.68
     tidigare
    0.68
     previamente
    0.67
    Activations Density 0.312%

    No Known Activations