© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 107806
    Prev
    Next
    INDEX
    Explanations

    the excessive use of the word "Most"

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

    majority or superlative statements

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Aim
    -0.60
     illustration
    -0.53
    hms
    -0.52
    ungsver
    -0.52
     Hug
    -0.52
     dimension
    -0.52
     aim
    -0.51
     EGL
    -0.51
     slat
    -0.50
    お話
    -0.50
    POSITIVE LOGITS
     Most
    1.13
    Most
    1.11
    MOST
    0.68
     MOST
    0.62
    ientôt
    0.56
    Mostly
    0.52
    的最
    0.51
    most
    0.51
     meeste
    0.48
    Greatest
    0.46
    Activations Density 0.009%

    No Known Activations