© 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. 12585
    Prev
    Next
    INDEX
    Explanations

    references to online forums and discussion boards

    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
    AddTagHelper
    -0.52
     reno
    -0.39
    🎁
    -0.38
    rrggbb
    -0.38
    TokenNameLBRACE
    -0.35
     importe
    -0.35
     Kiki
    -0.35
    lended
    -0.35
    gypti
    -0.35
    letoe
    -0.34
    POSITIVE LOGITS
     forum
    2.56
     Forum
    2.41
     forums
    2.36
    Forum
    2.34
    forum
    2.30
     FORUM
    2.20
     Forums
    2.14
    FORUM
    1.93
    Forums
    1.92
    forums
    1.77
    Activations Density 0.216%

    No Known Activations