© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6482
    Prev
    Next
    INDEX
    Explanations

    sentences that include punctuation marks, particularly periods

    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
    webElementXpaths
    -0.46
    aarrggbb
    -0.39
    migrationBuilder
    -0.38
    uxxxx
    -0.38
    WindowConstants
    -0.35
    stopPropagation
    -0.35
    complexContent
    -0.33
    +#+#
    -0.32
    Autoritní
    -0.32
    opsida
    -0.31
    POSITIVE LOGITS
     and
    1.26
    and
    1.24
     which
    1.16
    which
    1.14
    with
    1.11
     with
    1.08
     that
    0.98
    that
    0.98
     to
    0.96
     but
    0.96
    Activations Density 0.941%

    No Known Activations