© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13712
    Prev
    Next
    INDEX
    Explanations

    references to mechanical components and their functions

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

    before "of," "as," "that," "s"

    np_acts-logits-general · gemini-2.0-flash

    describing components and their connections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     institutional
    -0.42
     repatriation
    -0.40
     kasarigan
    -0.40
    ocarditis
    -0.38
     repatri
    -0.38
    SNAPSHOT
    -0.37
    RuntimeException
    -0.37
     international
    -0.37
    setTypeface
    -0.36
     social
    -0.36
    POSITIVE LOGITS
    webElementXpaths
    0.65
     removable
    0.60
    IntoConstraints
    0.55
     unob
    0.54
    Билгалдахарш
    0.52
    adjustable
    0.52
     Removable
    0.52
     bagian
    0.50
     Convenience
    0.50
    designed
    0.49
    Activations Density 0.819%

    No Known Activations