© 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. 11442
    Prev
    Next
    INDEX
    Explanations

    symbols and annotations related to experimental data and statistical significance

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

    Statistical significance markers

    np_acts-logits-general · gemini-2.0-flash

    statistical significance markers

    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
    AndEndTag
    -0.60
    دانشنامهٔ
    -0.60
    contentLoaded
    -0.56
     resourceCulture
    -0.52
     contextLoads
    -0.52
    الحياه
    -0.51
     فريبيس
    -0.50
     صوتيه
    -0.50
     Waray
    -0.49
    ThroughAttribute
    -0.48
    POSITIVE LOGITS
    **
    1.13
     **
    1.08
    (**
    0.79
    †
    0.79
     *
    0.77
    ***
    0.76
     †
    0.73
     ***
    0.70
    .**
    0.68
    **.
    0.67
    Activations Density 0.665%

    No Known Activations