© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3254
    Prev
    Next
    INDEX
    Explanations

    syntax and structure related to computer programming or data processing commands

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

    mathematical and technical notation with special characters and symbolic expressions.

    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
    Autoritní
    -0.48
    rungsseite
    -0.38
    entibus
    -0.36
     étoit
    -0.34
     piatta
    -0.33
    AddTagHelper
    -0.33
    ruik
    -0.32
    mettere
    -0.32
    ὸν
    -0.32
     pouvoit
    -0.32
    POSITIVE LOGITS
    )."
    1.85
    .)
    1.84
    )</
    1.84
    !)
    1.82
    ).
    1.78
    ?)
    1.75
    »)
    1.74
    )",
    1.73
    ),"
    1.72
    )".
    1.71
    Activations Density 7.276%

    No Known Activations