© 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. 11773
    Prev
    Next
    INDEX
    Explanations

    key events and highlights from experiences or reports

    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
     atualmente
    -0.72
     currently
    -0.71
    currently
    -0.69
     actuellement
    -0.68
     obecnie
    -0.68
     Currently
    -0.66
     actualmente
    -0.63
     attualmente
    -0.62
    Currently
    -0.61
     actualidad
    -0.61
    POSITIVE LOGITS
     was
    1.35
     did
    1.13
     gave
    0.98
     didn
    0.97
     took
    0.97
     lacked
    0.97
     went
    0.93
     wasn
    0.92
     consisted
    0.86
     were
    0.86
    Activations Density 3.422%

    No Known Activations