© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 9649
    Prev
    Next
    INDEX
    Explanations

    occurrences of tables in the document

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

    HTML table tags and references

    np_acts-logits-general · gemini-2.0-flash

    table and code markup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BOOST
    -0.48
    innovation
    -0.47
     boosts
    -0.47
    suicide
    -0.46
    segmentation
    -0.46
    innoc
    -0.46
    passion
    -0.45
    Nem
    -0.45
    creds
    -0.45
    excess
    -0.45
    POSITIVE LOGITS
     table
    2.45
     Table
    2.25
    Table
    2.25
    table
    2.22
     tables
    1.88
    TABLE
    1.85
     TABLE
    1.77
     Tables
    1.73
    getTable
    1.56
    Tables
    1.54
    Activations Density 0.192%

    No Known Activations