© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 12-GEMMASCOPE-RES-16K
    11. 10393
    Prev
    Next
    INDEX
    Explanations

    references to high-quality or top selections in various contexts

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

    superlative phrases describing excellence or superiority, particularly "the best" and related expressions of highest quality.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    phrases signaling top-tier quality, prestige, or elite status.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.57
     fie
    -0.47
    transQ
    -0.47
    日閲覧
    -0.47
    AccessorTable
    -0.46
    *);
    -0.45
    Française
    -0.45
     ControllerBase
    -0.45
    fie
    -0.45
    Sucesor
    -0.44
    POSITIVE LOGITS
    quality
    0.50
     quality
    0.49
     kwaliteit
    0.48
    SBATCH
    0.48
     berkualitas
    0.48
     kvalit
    0.47
     calidad
    0.44
    QUALITY
    0.44
     qualidade
    0.44
     wspania
    0.44
    Activations Density 0.449%

    No Known Activations