© 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. 27-GEMMASCOPE-RES-16K
    11. 8101
    Prev
    Next
    INDEX
    Explanations

    structured assessments or rankings related to evaluation criteria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endwhile
    -0.42
     chuva
    -0.41
     ontem
    -0.39
    rimônio
    -0.38
     oídos
    -0.38
    privileged
    -0.38
    moveToFirst
    -0.37
    Especificações
    -0.37
     ninguém
    -0.37
    ุ่น
    -0.37
    POSITIVE LOGITS
     whether
    1.12
     ability
    0.93
    whether
    0.86
    是否
    0.85
     effectiveness
    0.84
     Whether
    0.83
    Whether
    0.82
     насколько
    0.81
     degree
    0.80
     likelihood
    0.78
    Activations Density 1.116%

    No Known Activations