© 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. 16-GEMMASCOPE-RES-16K
    11. 12985
    Prev
    Next
    INDEX
    Explanations

    elements and qualities of writing style and language clarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.56
     незавершена
    -0.47
    ppuden
    -0.37
    ">—
    -0.36
    unteer
    -0.36
    idea
    -0.35
     poveznice
    -0.35
     idea
    -0.35
    KommentareTeilen
    -0.35
     estekak
    -0.34
    POSITIVE LOGITS
     propOrder
    0.73
     language
    0.65
    MigrationBuilder
    0.63
     diction
    0.59
     prose
    0.55
     written
    0.54
     metaphors
    0.54
     sentences
    0.54
     linguagem
    0.53
     wording
    0.53
    Activations Density 0.248%

    No Known Activations