© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15258
    Prev
    Next
    INDEX
    Explanations

    links and references to external resources

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

    Links, specifically URLs in the text

    np_acts-logits-general · gemini-2.0-flash

    website links and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.83
     propOrder
    -0.69
    fromnode
    -0.66
    AutoScaleMode
    -0.62
    verifyException
    -0.60
    enterOuterAlt
    -0.59
    IsContent
    -0.57
    AxisAlignment
    -0.54
    IntoConstraints
    -0.54
    LayoutStyle
    -0.53
    POSITIVE LOGITS
     https
    0.48
    https
    0.44
    link
    0.44
     link
    0.44
    ilyn
    0.43
     Google
    0.43
     http
    0.43
    deselect
    0.41
    Архівовано
    0.41
    同期
    0.40
    Activations Density 0.883%

    No Known Activations