© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 14062
    Prev
    Next
    INDEX
    Explanations

    references to the Bootstrap framework and associated libraries in a web development context

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

    Code related to web frameworks

    np_acts-logits-general · gemini-2.0-flash

    protobuf unknown fields handling

    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
    Slf
    -0.49
     AUSSI
    -0.46
    COUVER
    -0.43
    ;#
    -0.42
     Segel
    -0.42
    {~
    -0.40
     createState
    -0.39
     direta
    -0.38
     Zivil
    -0.38
    -
    -0.38
    POSITIVE LOGITS
    OGND
    0.76
    StructEnd
    0.63
    uxxxx
    0.62
    httphttps
    0.61
    хьтан
    0.59
    sizeCache
    0.58
    quième
    0.57
     незавершена
    0.57
     MenuView
    0.57
    WriteBarrier
    0.56
    Activations Density 0.566%

    No Known Activations