© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 5484
    Prev
    Next
    INDEX
    Explanations

    geometric shapes, particularly squares and triangles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    揄
    -0.44
    참고
    -0.43
    thrift
    -0.40
     Udo
    -0.38
    TLC
    -0.37
    一位
    -0.36
    inSlope
    -0.36
    after
    -0.35
     been
    -0.35
     After
    -0.34
    POSITIVE LOGITS
     square
    1.93
     Square
    1.81
     SQUARE
    1.73
    Square
    1.72
    square
    1.63
    SQUARE
    1.59
     squares
    1.57
     Squares
    1.40
    quare
    1.34
    Squares
    1.34
    Activations Density 0.237%

    No Known Activations