© 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. 23-GEMMASCOPE-RES-16K
    6. 9425
    Prev
    Next
    INDEX
    Explanations

    references to various stages and scenes in narratives or performances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     armée
    -0.56
     grecque
    -0.48
    tisgarh
    -0.47
     Política
    -0.45
     kiệm
    -0.45
     Unidas
    -0.44
     mathematician
    -0.44
    Спољашње
    -0.43
     prieten
    -0.43
    pañol
    -0.43
    POSITIVE LOGITS
     STAGE
    0.85
     Stage
    0.83
     stage
    0.81
     stages
    0.79
     Scene
    0.79
    Stage
    0.78
     PHASE
    0.78
     Phase
    0.77
     scene
    0.77
    Phase
    0.73
    Activations Density 0.552%

    No Known Activations