© 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. 30-GEMMASCOPE-RES-16K
    11. 12646
    Prev
    Next
    INDEX
    Explanations

    references to contribution and authorship in research documents

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

    Writing and drafting manuscripts

    np_acts-logits-general · gemini-2.0-flash

    drafting and writing manuscripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     empreg
    -0.35
    Duración
    -0.35
     תע
    -0.35
    occasione
    -0.34
     employed
    -0.34
     alkalmaz
    -0.33
    DispatchToProps
    -0.32
     nadzieję
    -0.31
    ouvre
    -0.31
     saluti
    -0.31
    POSITIVE LOGITS
     draft
    1.70
     drafts
    1.40
    draft
    1.37
     Draft
    1.34
     preliminary
    1.30
    Draft
    1.28
     DRAFT
    1.27
    DRAFT
    1.16
     drafted
    1.09
     rough
    1.09
    Activations Density 0.700%

    No Known Activations