© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 12946
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and references to URLs

    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
     BoxFit
    -0.48
    expandindo
    -0.47
    Tikang
    -0.43
    InputBorder
    -0.41
     Lightboxes
    -0.41
    ItemBackground
    -0.41
    WithMany
    -0.40
    DECREF
    -0.40
    にほんブログ村
    -0.39
    TextSpan
    -0.38
    POSITIVE LOGITS
    io
    0.71
    xyz
    0.59
     io
    0.59
    ai
    0.56
    IO
    0.56
    icu
    0.53
     IO
    0.52
     xyz
    0.52
    space
    0.51
    rocks
    0.50
    Activations Density 0.224%

    No Known Activations