© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3618
    Prev
    Next
    INDEX
    Explanations

    references to hyperlinks or URLs in text, often indicated by words like "link" or phrases related to web navigation and page elements.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @myinzi123

    references to links or URL connections

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

    Tokens that are the word "link" or a variant of it

    np_acts-logits-general · gemini-2.0-flash

    link below or link to

    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
    __":
    -0.52
    evos
    -0.49
    __":
    -0.48
     Drey
    -0.44
    QMetaType
    -0.44
    )")
    -0.44
    .");
    -0.43
    AppCompat
    -0.43
    didSet
    -0.42
    initialState
    -0.41
    POSITIVE LOGITS
    link
    1.38
     link
    1.38
     Link
    1.36
    Link
    1.34
     LINK
    1.24
    LINK
    1.23
     links
    1.21
    links
    1.21
     LINKS
    1.20
     Links
    1.20
    Activations Density 0.054%

    No Known Activations