© 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. 30-GEMMASCOPE-RES-16K
    11. 10041
    Prev
    Next
    INDEX
    Explanations

    commands and structures related to makefile syntax and its configuration

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

    Code snippets with special characters

    np_acts-logits-general · gemini-2.0-flash

    compatible partitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    //
    -0.43
    Hats
    -0.34
    애
    -0.33
     národ
    -0.33
     nest
    -0.32
    Iz
    -0.31
    Osc
    -0.31
    #
    -0.31
    رائ
    -0.30
     OPERATION
    -0.30
    POSITIVE LOGITS
    parsedMessage
    0.63
    出版年
    0.61
     CURLOPT
    0.59
    UrlResolution
    0.54
    OCCURRED
    0.54
    dormit
    0.52
    ayage
    0.52
    WriteBarrier
    0.51
    IndentedString
    0.51
    uxxxx
    0.49
    Activations Density 0.160%

    No Known Activations