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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 5151
    Prev
    Next
    INDEX
    Explanations

    references to flying or flight-related concepts

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

    "fly" and flying

    np_acts-logits-general · gemini-2.0-flash

    flying objects and creatures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرياضيه
    -0.91
    BeginInit
    -0.65
    ]")]
    -0.64
     Normdatei
    -0.61
     ISNI
    -0.61
    Personensuche
    -0.61
    RefNanny
    -0.60
     Gend
    -0.60
    SourceChecksum
    -0.59
    Enders
    -0.58
    POSITIVE LOGITS
     fly
    1.08
     FLY
    1.00
    FLY
    0.98
     Fly
    0.97
    Fly
    0.90
    fly
    0.86
     flew
    0.85
     flying
    0.82
     flies
    0.81
     Flying
    0.79
    Activations Density 0.211%

    No Known Activations