© 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. 41-GEMMASCOPE-RES-16K
    11. 8392
    Prev
    Next
    INDEX
    Explanations

    words associated with legal or regulatory concepts and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageOf
    -0.47
    følgelig
    -0.43
    hadiran
    -0.43
    сторія
    -0.40
    น์
    -0.39
    mampuan
    -0.38
    zwischen
    -0.38
    teps
    -0.37
    hidupan
    -0.36
    complexContent
    -0.36
    POSITIVE LOGITS
    ing
    3.56
    ING
    2.31
    ی
    1.56
    ة
    1.45
    ingi
    1.16
    ingar
    1.13
    ingl
    1.12
    inges
    1.09
    いる
    1.04
    ingh
    1.04
    Activations Density 1.043%

    No Known Activations