© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 1665
    Prev
    Next
    INDEX
    Explanations

    HTML/XML tags and their attributes

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

    The token "label" and related terms

    np_acts-logits-general · gemini-2.0-flash

    label in html and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    through
    -0.40
    will
    -0.40
    Through
    -0.39
    time
    -0.38
    extrême
    -0.37
    Perfect
    -0.36
     meisten
    -0.36
    getD
    -0.36
    in
    -0.36
     (!(
    -0.35
    POSITIVE LOGITS
     Label
    0.95
    getLabel
    0.90
     LABEL
    0.87
     jLabel
    0.81
     lbl
    0.79
     Labels
    0.79
     label
    0.78
    ILabel
    0.76
    InputLabel
    0.75
     Labeling
    0.73
    Activations Density 0.187%

    No Known Activations