© 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 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. 8660
    Prev
    Next
    INDEX
    Explanations

    information related to urban structures and facilities

    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
     مرئيه
    -0.64
    OGND
    -0.64
    principalColumn
    -0.61
    tangentMode
    -0.57
    KommentareTeilen
    -0.56
    ThroughAttribute
    -0.55
    SharedCtor
    -0.54
    enumii
    -0.54
     unknownFields
    -0.54
    +#+#
    -0.53
    POSITIVE LOGITS
     housing
    1.09
     complete
    0.97
     hosting
    0.96
     equipped
    0.95
     accommodating
    0.93
     offering
    0.89
    complete
    0.83
     featuring
    0.80
    housing
    0.80
     serving
    0.77
    Activations Density 0.411%

    No Known Activations