© 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. 6314
    Prev
    Next
    INDEX
    Explanations

    phrases indicating various classifications or categories

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

    "types of" followed by nouns

    np_acts-logits-general · gemini-2.0-flash

    types of category

    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
    ientras
    -0.58
     fotográfico
    -0.57
     bordada
    -0.56
     térmica
    -0.55
     Kebijakan
    -0.55
     fotográfica
    -0.53
     razonable
    -0.52
     embaraz
    -0.51
     financeira
    -0.51
     cerah
    -0.50
    POSITIVE LOGITS
     types
    1.20
     kinds
    1.07
     Kinds
    0.96
    kinds
    0.95
     Types
    0.93
    types
    0.87
    Types
    0.87
     type
    0.86
     TYPES
    0.84
    Kinds
    0.82
    Activations Density 0.490%

    No Known Activations