© 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. 12-GEMMASCOPE-RES-16K
    11. 1778
    Prev
    Next
    INDEX
    Explanations

    terms related to separation and distinguishing components from one another

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 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
     Clint
    -0.81
    примеча
    -0.80
     Hawkeye
    -0.77
    Clint
    -0.77
     NSCoder
    -0.72
     dext
    -0.69
     Dak
    -0.69
     onOptions
    -0.68
     Fittings
    -0.67
    Industrie
    -0.67
    POSITIVE LOGITS
     Separation
    1.28
     separation
    1.25
    Separation
    1.19
     separating
    1.19
     separations
    1.18
     Separ
    1.11
     separates
    1.11
     separ
    1.10
    PARATION
    1.10
     Separator
    1.09
    Activations Density 0.138%

    No Known Activations