© 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. 31-GEMMASCOPE-RES-16K
    11. 13156
    Prev
    Next
    INDEX
    Explanations

    features and specifications related to advanced automotive technology

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

    promotional or marketing text describing vehicle features and specifications.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    positive descriptive adjectives and superlatives used to praise vehicle features and performance.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geplaatst
    -0.53
    Explicación
    -0.44
    ///</
    -0.41
     coches
    -0.41
    Życiorys
    -0.40
    ruptedException
    -0.40
     actividad
    -0.40
     mindig
    -0.40
     efecto
    -0.39
     automó
    -0.39
    POSITIVE LOGITS
     features
    0.91
     price
    0.85
     durability
    0.83
    features
    0.77
     Features
    0.77
     versatility
    0.77
     performance
    0.76
     ergonomics
    0.75
    price
    0.72
     robustness
    0.72
    Activations Density 0.316%

    No Known Activations