© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 5618
    Prev
    Next
    INDEX
    Explanations

    structural patterns and key-value assignments in code-like data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Apalagi
    -0.62
     mukana
    -0.60
    useNewUrlParser
    -0.59
    ----+
    -0.58
     oscura
    -0.53
    membre
    -0.53
     Boletín
    -0.51
     textStatus
    -0.51
    maco
    -0.51
    steps
    -0.51
    POSITIVE LOGITS
    IntoConstraints
    0.99
     autorytatywna
    0.84
    migrationBuilder
    0.75
     disambiguazione
    0.65
     propOrder
    0.65
    principalTable
    0.64
    GEBURTSDATUM
    0.61
     transfieras
    0.60
    pushFollow
    0.57
    tangentMode
    0.57
    Activations Density 0.382%

    No Known Activations