© 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
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 12342
    Prev
    Next
    INDEX
    Explanations

    numerical ranges and their representations, specifically focusing on scores and statistics associated with events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.46
    IntoConstraints
    -0.45
    UnusedPrivate
    -0.42
     ſtand
    -0.41
     Normdatei
    -0.40
    bootstrapcdn
    -0.39
    ujudkan
    -0.37
    ISODE
    -0.37
     Raise
    -0.36
     pères
    -0.36
    POSITIVE LOGITS
     SwitchCompat
    0.54
     ویکی‌پدیای
    0.50
    kháu
    0.44
    Portale
    0.43
    Autoritní
    0.43
     الموا
    0.40
    хьтан
    0.40
    UseVisualStyle
    0.39
    DeleteBehavior
    0.38
    0.38
    Activations Density 0.142%

    No Known Activations