© 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. 13654
    Prev
    Next
    INDEX
    Explanations

    references to board decisions and approvals

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

    "board," "committee," or "cabinet"

    np_acts-logits-general · gemini-2.0-flash

    governing body actions

    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
    OGND
    -0.64
    MethodManager
    -0.63
     للاسماء
    -0.57
    enderror
    -0.57
    Philippines
    -0.55
    PerformLayout
    -0.54
     Philippines
    -0.53
    imaginary
    -0.53
    ագրություններ
    -0.52
    addContainerGap
    -0.52
    POSITIVE LOGITS
     committee
    0.53
     Committee
    0.50
     Council
    0.50
     unanimously
    0.48
     council
    0.47
    Council
    0.46
     Meeting
    0.45
     meeting
    0.44
    committee
    0.44
     Board
    0.43
    Activations Density 0.307%

    No Known Activations