© 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
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 9808
    Prev
    Next
    INDEX
    Explanations

    keywords related to organizations, tasks, and structures within various contexts and fields

    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
    ientras
    -0.47
     enfans
    -0.40
     Bewußt
    -0.39
     pouvoit
    -0.39
     sudad
    -0.39
     auroit
    -0.36
    Dobrý
    -0.36
     dimenti
    -0.36
    日発売
    -0.36
    pantalón
    -0.35
    POSITIVE LOGITS
    躇
    0.79
    fortawesome
    0.65
     Wallflower
    0.61
    TargetException
    0.61
    gebob
    0.58
    Leary
    0.57
    TacToe
    0.56
    jetunion
    0.55
    IntoConstraints
    0.55
    ElementException
    0.55
    Activations Density 4.829%

    No Known Activations