© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 13812
    Prev
    Next
    INDEX
    Explanations

    references to height and airborne movement

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

    preceding "air."

    np_acts-logits-general · gemini-2.0-flash

    air, sky, atmosphere

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElementXpaths
    -0.69
    WebServlet
    -0.67
     Offisielt
    -0.65
    DockStyle
    -0.62
    RenderAtEndOf
    -0.57
     CURIAM
    -0.56
    Activités
    -0.55
    futbolista
    -0.53
    isla
    -0.53
    دانشنامهٔ
    -0.53
    POSITIVE LOGITS
     air
    2.69
    air
    2.15
    Air
    1.81
     Air
    1.80
     AIR
    1.65
     aire
    1.63
    AIR
    1.58
     lucht
    1.49
     udara
    1.49
     Luft
    1.47
    Activations Density 0.249%

    No Known Activations