© 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-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 9765
    Prev
    Next
    INDEX
    Explanations

    HTML link attributes related to stylesheets and icons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HasFactory
    -0.83
    MigrationBuilder
    -0.79
     GenerationType
    -0.78
    ContentAlignment
    -0.76
    +#+#
    -0.75
    TagMode
    -0.74
     <>",
    -0.71
    ValueGeneration
    -0.70
    //
    -0.69
    AndPassword
    -0.68
    POSITIVE LOGITS
     rel
    1.46
     REL
    0.89
    rel
    0.88
     Rel
    0.88
    REL
    0.82
    Relations
    0.77
    Rel
    0.77
     relations
    0.71
    Rela
    0.69
     Rela
    0.68
    Activations Density 0.027%

    No Known Activations