© 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. 12-GEMMASCOPE-RES-16K
    11. 3992
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significant features or characteristics of subjects presented in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OMITBAD
    -0.57
     Италијани
    -0.53
     MMC
    -0.53
    GenerationType
    -0.50
    NOPQRST
    -0.50
     CURIAM
    -0.49
    MMC
    -0.49
    ScopeManager
    -0.48
     ria
    -0.47
     AspNetCore
    -0.47
    POSITIVE LOGITS
     razón
    0.50
     dôle
    0.49
     Wikiseite
    0.49
     wichtigste
    0.49
     spôso
    0.47
     ventaja
    0.47
     voordeel
    0.46
     terbesar
    0.46
     facteur
    0.46
     största
    0.46
    Activations Density 0.433%

    No Known Activations