Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 20400
    Prev
    Next
    INDEX
    Explanations

    instances of the word "im" or variations thereof in mathematical contexts

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

    im / Im

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    carteles
    -0.75
    étoit
    -0.65
    AddHtmlAttribute
    -0.65
    cetines
    -0.65
     enfans
    -0.64
    aucune
    -0.64
    ſelves
    -0.64
     Theſe
    -0.63
     للمعارف
    -0.63
     feroit
    -0.62
    POSITIVE LOGITS
    im
    0.82
     IM
    0.77
     Im
    0.75
     im
    0.75
    IM
    0.67
    Im
    0.60
     M
    0.57
     Imm
    0.56
     m
    0.55
    I
    0.54
    Activations Density 0.016%

    No Known Activations