© 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. 5598
    Prev
    Next
    INDEX
    Explanations

    references to patents or patent numbers in the text

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

    abbreviations for "United States" (U.S.).

    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
     ModelExpression
    -0.59
    帖最后由
    -0.53
    ➟
    -0.53
    richTextPanel
    -0.50
    SBATCH
    -0.48
    tanleria
    -0.47
    DoubleQuotes
    -0.47
    Склад
    -0.46
     initComponents
    -0.46
     poveznice
    -0.46
    POSITIVE LOGITS
     U
    0.51
    turn
    0.45
     turn
    0.43
    قایناق‌لار
    0.40
    titure
    0.37
    حياته
    0.36
     unmute
    0.35
     US
    0.35
     @"/
    0.33
    rungsseite
    0.33
    Activations Density 0.204%

    No Known Activations