© 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. 31-GEMMASCOPE-RES-131K
    6. 111105
    Prev
    Next
    INDEX
    Explanations

    references to wings and their symbolic or metaphorical significance

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

    wings and flight

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Where Avali 2?

    No Comments

    Negative Logits
     EconPapers
    -0.69
    adaptiveStyles
    -0.61
    Hentet
    -0.58
     ſen
    -0.56
    httphttps
    -0.55
     Efq
    -0.54
    AsUp
    -0.52
    ſammen
    -0.51
     Monfieur
    -0.50
     trolley
    -0.50
    POSITIVE LOGITS
     wings
    1.27
     wing
    1.05
     Wings
    0.93
    wings
    0.89
     flight
    0.85
    Wings
    0.83
     Wing
    0.82
     flapping
    0.82
     sayap
    0.81
     flying
    0.77
    Activations Density 0.034%

    No Known Activations