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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 96685
    Prev
    Next
    INDEX
    Explanations

    the word "I" in various contexts, indicating a focus on first-person perspective

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

    conjunctions and symbols

    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
     avoient
    -0.61
     auroit
    -0.56
     enfans
    -0.56
     feroit
    -0.54
     nemlig
    -0.52
     étoient
    -0.50
     seyn
    -0.49
     imidlertid
    -0.45
     hunne
    -0.44
     setUsername
    -0.43
    POSITIVE LOGITS
     and
    0.76
     i
    0.73
    和
    0.61
     I
    0.57
    I
    0.55
     и
    0.54
     和
    0.54
     وتسجيلات
    0.53
     AND
    0.52
    ************/
    0.52
    Activations Density 0.000%

    No Known Activations