© 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. 10-GEMMASCOPE-RES-16K
    11. 4300
    Prev
    Next
    INDEX
    Explanations

    instances of the word "format" and its related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mouse
    -0.39
    Pe
    -0.37
    Personne
    -0.36
    Nin
    -0.35
    Mouse
    -0.35
     Thi
    -0.35
    PublicKey
    -0.35
    expandindo
    -0.35
    nonzero
    -0.35
     النا
    -0.35
    POSITIVE LOGITS
     format
    2.30
     Format
    2.28
    format
    2.19
    Format
    2.17
     FORMAT
    2.08
     formats
    2.05
     Formats
    2.03
    FORMAT
    1.80
    formats
    1.68
    格式
    1.66
    Activations Density 0.094%

    No Known Activations