© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 6339
    Prev
    Next
    INDEX
    Explanations

    terms associated with all-star games and player recognition in sports

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

    "All-Star" and sports leagues

    np_acts-logits-general · gemini-2.0-flash

    all-star break contests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.57
    IntoConstraints
    -0.50
     ſtate
    -0.50
    #+#
    -0.49
    +#+#
    -0.49
     '{@
    -0.48
    OCCURRED
    -0.48
    WebElementEntity
    -0.48
     peores
    -0.47
     HasFactory
    -0.47
    POSITIVE LOGITS
    InputBorder
    0.46
    multirow
    0.45
    JspWriter
    0.40
    SequentialGroup
    0.37
     برانيه
    0.36
    ActionCreators
    0.34
    WithMany
    0.34
    ><!--
    0.33
     voting
    0.32
    disposed
    0.32
    Activations Density 0.222%

    No Known Activations