© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 2660
    Prev
    Next
    INDEX
    Explanations

    programming constructs and syntax related to conditional statements and function definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.75
    TypedDataSet
    -0.68
    EndInit
    -0.61
    PerformLayout
    -0.57
    UserScript
    -0.54
    AndEndTag
    -0.52
    ロウィン
    -0.52
    Autoritní
    -0.50
     كومونز
    -0.50
     Wiktionnaire
    -0.49
    POSITIVE LOGITS
    C
    0.63
    A
    0.59
     C
    0.58
    B
    0.58
     A
    0.54
     huruf
    0.54
     letter
    0.49
     B
    0.48
    D
    0.48
    Letter
    0.47
    Activations Density 1.912%

    No Known Activations