© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2868
    Prev
    Next
    INDEX
    Explanations

    HTTP-related terms and concepts

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

    "http" or "HTTP" strings

    np_acts-logits-general · gemini-2.0-flash

    http urls and requests

    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
    oredCriteria
    -0.62
    BindView
    -0.60
    parsedMessage
    -0.59
    VertexArray
    -0.56
    featureID
    -0.56
    endregion
    -0.56
    withIdentifier
    -0.54
    area
    -0.54
    ace
    -0.52
    orius
    -0.52
    POSITIVE LOGITS
    http
    1.30
    Http
    1.23
     http
    1.16
     Http
    1.13
    HTTP
    1.05
     HTTP
    1.04
    https
    0.90
    ttp
    0.85
     https
    0.82
    ttps
    0.75
    Activations Density 0.069%

    No Known Activations