© 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. 4609
    Prev
    Next
    INDEX
    Explanations

    references to research methods and results in scientific contexts

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

    acronyms and specialized terminology related to scientific or technical domains.

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

    family-related research survey data and academic/technical documentation describing studies and methodologies.

    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
     EconPapers
    -0.75
    rungsseite
    -0.59
    InjectAttribute
    -0.55
    libft
    -0.51
    httphttps
    -0.50
    AddHtmlAttribute
    -0.49
    ViewImports
    -0.48
    EndContext
    -0.48
    esez
    -0.48
    [@BOS@]
    -0.47
    POSITIVE LOGITS
     because
    0.97
     while
    0.96
     whereas
    0.95
     despite
    0.83
     during
    0.83
     although
    0.82
     tandis
    0.80
     since
    0.79
     mentre
    0.79
     mientras
    0.78
    Activations Density 3.999%

    No Known Activations