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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10668
    Prev
    Next
    INDEX
    Explanations

    references to numerical models and their properties

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

    phrases that describe conditional relationships where one parameter affects another parameter's value.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    consensus
    -0.39
    reshape
    -0.38
    latest
    -0.38
    rawtypes
    -0.37
    team
    -0.36
    setModal
    -0.36
    améli
    -0.36
    mond
    -0.36
    too
    -0.36
    wo
    -0.35
    POSITIVE LOGITS
    AutoScaleMode
    0.56
     autorytatywna
    0.50
     transfieras
    0.50
    sizeCache
    0.49
    transQ
    0.49
     oprot
    0.48
    OGND
    0.47
    mybatisplus
    0.46
    Примітки
    0.43
    AsUp
    0.43
    Activations Density 0.372%

    No Known Activations