© 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. 41-GEMMASCOPE-RES-16K
    11. 12957
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting symbols used in citations or references

    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
     formally
    -0.45
     صوتيه
    -0.43
     utafitiHapana
    -0.38
    XDECREF
    -0.37
    GIVEREF
    -0.35
    UpInside
    -0.35
    habilit
    -0.35
     confinement
    -0.34
     Reverso
    -0.34
     outputs
    -0.33
    POSITIVE LOGITS
    rawDesc
    0.40
     princesas
    0.40
     смета
    0.39
    ího
    0.39
    owulf
    0.38
     potrafi
    0.38
     transfieras
    0.37
    uxxxx
    0.36
    WORTH
    0.36
    IsMutable
    0.36
    Activations Density 0.132%

    No Known Activations