© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 58763
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "avi" or related variations, likely indicating a focus on aviation or related subjects

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

    aviator, avium, Aviapolis

    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
     valentín
    -0.53
     Gestión
    -0.48
    urlencoded
    -0.48
     crecimiento
    -0.48
     florales
    -0.48
     efectiva
    -0.47
     pertenece
    -0.47
     estratégica
    -0.46
     positivas
    -0.45
     Thanh
    -0.45
    POSITIVE LOGITS
     Avi
    2.50
    Avi
    2.30
     avi
    2.19
    avi
    1.63
     AVI
    1.63
     aviator
    1.49
    AVI
    1.36
     Avian
    0.87
    Av
    0.81
     Aviation
    0.80
    Activations Density 0.004%

    No Known Activations