© 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. 8451
    Prev
    Next
    INDEX
    Explanations

    elements related to themes and their exploration in the context of artistic or literary works

    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
     Glied
    -0.33
    EnumMember
    -0.30
     thất
    -0.30
     obvio
    -0.29
     autoridad
    -0.28
    zusetzen
    -0.28
     Derechos
    -0.28
     Comprometido
    -0.27
     Quincy
    -0.27
     subterrá
    -0.27
    POSITIVE LOGITS
     topics
    0.91
     themes
    0.81
    Topics
    0.78
     Topics
    0.73
    topics
    0.70
     topic
    0.68
     temáticas
    0.67
     thematic
    0.66
     Themes
    0.66
     theme
    0.66
    Activations Density 0.900%

    No Known Activations