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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 5964
    Prev
    Next
    INDEX
    Explanations

    non-English characters and error messages related to programming or software issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     maravillas
    -0.53
     samfun
    -0.53
     vrijwilli
    -0.52
     dignité
    -0.50
     Sosial
    -0.49
     leçon
    -0.49
     tilbud
    -0.49
     keben
    -0.49
    horabuena
    -0.48
     solidarité
    -0.48
    POSITIVE LOGITS
     للمعارف
    0.77
     faſt
    0.73
     ſte
    0.72
    endpush
    0.67
     ſch
    0.66
     ſta
    0.64
     itſelf
    0.64
     ſche
    0.63
     ſur
    0.63
    </tfoot>
    0.60
    Activations Density 0.041%

    No Known Activations