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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 12-GEMMASCOPE-RES-65K
    11. 13755
    Prev
    Next
    INDEX
    Explanations

    references to blogs, posts, or anthropological content related to educational resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    graphiques
    -0.47
     effectivement
    -0.44
     câncer
    -0.43
    rayage
    -0.41
     Stornier
    -0.41
    ほど
    -0.40
     vidrio
    -0.40
    tenberg
    -0.39
     liền
    -0.39
     salida
    -0.38
    POSITIVE LOGITS
     autorytatywna
    0.97
     intptr
    0.83
     Signalez
    0.77
     CreateTagHelper
    0.76
    BibitemShut
    0.74
     everyday
    0.73
    enderror
    0.73
    醐
    0.72
     eventdata
    0.72
    featureID
    0.71
    Activations Density 0.094%

    No Known Activations