© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8214
    Prev
    Next
    INDEX
    Explanations

    occurrences and references to "labels" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    with
    -0.51
    électricité
    -0.47
    time
    -0.47
    Five
    -0.47
    atmosphère
    -0.46
    extrême
    -0.45
     Goodrich
    -0.45
    com
    -0.44
    times
    -0.44
    five
    -0.43
    POSITIVE LOGITS
     Label
    1.38
     label
    1.31
     LABEL
    1.30
     Labels
    1.23
    getLabel
    1.21
    label
    1.16
    Label
    1.13
     labels
    1.10
    setLabel
    1.10
    LABEL
    1.08
    Activations Density 0.050%

    No Known Activations