© 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. 9-GEMMASCOPE-RES-16K
    11. 10786
    Prev
    Next
    INDEX
    Explanations

    references to size or magnitude, specifically emphasizing the term "large."

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

    Following "large"

    np_acts-logits-general · gemini-2.0-flash

    large magnitude

    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
     Condi
    -0.56
     Odyssey
    -0.56
     chrono
    -0.53
    فية
    -0.53
    thio
    -0.52
    ActionMode
    -0.51
     sphinct
    -0.51
    DockStyle
    -0.50
    ToCheck
    -0.50
    awin
    -0.50
    POSITIVE LOGITS
     large
    1.91
    Large
    1.82
     Large
    1.78
    large
    1.78
     LARGE
    1.63
    LARGE
    1.52
     larger
    1.29
     Larger
    1.19
    Larger
    1.18
    larger
    1.15
    Activations Density 0.200%

    No Known Activations