© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 9685
    Prev
    Next
    INDEX
    Explanations

    specific terms and phrases related to scientific methods and observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tonode
    -0.37
    Réalisation
    -0.32
    ungsver
    -0.31
     planification
    -0.31
    SetTitle
    -0.30
    coche
    -0.29
     bedrijf
    -0.29
    Nationalité
    -0.28
    Computation
    -0.28
    Экономи
    -0.28
    POSITIVE LOGITS
     also
    0.73
    uxxxx
    0.56
     juga
    0.56
    weeb
    0.54
    Also
    0.52
    RTHOOK
    0.51
     kaarangay
    0.51
     também
    0.51
    also
    0.50
     فريبيس
    0.50
    Activations Density 0.879%

    No Known Activations