© 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. 5872
    Prev
    Next
    INDEX
    Explanations

    programming language constructs such as include statements, function definitions, and package declarations

    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
    A
    -0.42
    T
    -0.40
    .
    -0.39
     conquête
    -0.39
     yazılı
    -0.38
     pagină
    -0.38
     rač
    -0.38
    ,
    -0.37
     ış
    -0.37
     màn
    -0.37
    POSITIVE LOGITS
     himo
    0.97
    +#+
    0.96
    WithIOException
    0.93
    LikeLike
    0.91
    UnknownFieldSet
    0.90
    بوابة
    0.88
    
    0.85
    CloseOperation
    0.84
    tvguidetime
    0.84
    PYX
    0.83
    Activations Density 0.234%

    No Known Activations