© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 12233
    Prev
    Next
    INDEX
    Explanations

    syntactical structures and elements related to layout or design specifications in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    numeric values and dimensions in code (pixel measurements, coordinates, and size specifications).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.55
     TestBed
    -0.50
    הערות
    -0.49
    adaptiveStyles
    -0.48
    SceneManagement
    -0.47
    EnableWeb
    -0.46
    lanatory
    -0.45
    WebServlet
    -0.45
    참고
    -0.45
    addCriterion
    -0.45
    POSITIVE LOGITS
     sized
    0.36
     кстати
    0.35
     uParam
    0.35
     ویکی‌پدی
    0.34
    izr
    0.33
     excepted
    0.33
     Audiodateien
    0.32
    Width
    0.32
     thin
    0.32
     dashing
    0.31
    Activations Density 0.108%

    No Known Activations