© 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. 11-GEMMASCOPE-RES-16K
    11. 11532
    Prev
    Next
    INDEX
    Explanations

    references to divisions within organizations or legal contexts

    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
    Datuak
    -0.56
    OCCURRED
    -0.50
    原始内容存档于
    -0.50
    httphttps
    -0.45
    ambién
    -0.45
    béco
    -0.45
    ệm
    -0.45
     Kenn
    -0.44
     anthropogenic
    -0.42
    Nok
    -0.42
    POSITIVE LOGITS
     division
    1.40
     Division
    1.35
    Division
    1.25
    division
    1.25
     divisions
    1.17
     Divisions
    1.16
     DIVISION
    1.09
     divide
    1.05
    divisions
    1.03
     división
    1.02
    Activations Density 0.196%

    No Known Activations