© 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. 11-GEMMASCOPE-RES-16K
    11. 12956
    Prev
    Next
    INDEX
    Explanations

    patterns in alphanumeric data and specific sequences that appear to correlate with structured information, possibly related to identifiers or keys

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sweise
    -0.78
    zelfde
    -0.77
    ième
    -0.71
    iyle
    -0.70
    یتی
    -0.66
    нное
    -0.65
    iarkan
    -0.64
    ی
    -0.63
    iqué
    -0.61
    ه
    -0.61
    POSITIVE LOGITS
    <bos>
    2.47
    ekš
    0.67
    yszer
    0.66
    vény
    0.65
    JKLM
    0.63
    pośred
    0.63
     duyg
    0.60
    çası
    0.59
     שח
    0.59
     الاول
    0.59
    Activations Density 11.617%

    No Known Activations