© 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. 11-GEMMASCOPE-RES-16K
    6. 8458
    Prev
    Next
    INDEX
    Explanations

    references to physical representations of people or objects

    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
     services
    -0.33
     démocratie
    -0.30
     pulseras
    -0.30
     authors
    -0.30
    AUTHOR
    -0.29
    Author
    -0.29
     prefeitura
    -0.29
    mbitos
    -0.29
    services
    -0.28
     credit
    -0.28
    POSITIVE LOGITS
    OGND
    0.96
     disambiguazione
    0.79
    MessageOf
    0.78
     betweenstory
    0.76
    InputBorder
    0.75
     محفوظة
    0.74
    isContained
    0.73
     ब्रेकडाउन
    0.72
    IsContent
    0.71
    tagHelperRunner
    0.69
    Activations Density 0.354%

    No Known Activations