© 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. 22-GEMMASCOPE-RES-16K
    11. 3065
    Prev
    Next
    INDEX
    Explanations

    negative perceptions or impacts related to wind turbines

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

    Terms related to aesthetics or appearance

    np_acts-logits-general · gemini-2.0-flash

    aesthetic appearance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.90
    تفصیلات
    -0.58
    migrationBuilder
    -0.57
    الحياه
    -0.54
    mybatisplus
    -0.54
     chi̍t
    -0.53
     للتو
    -0.53
    GraphicsUnit
    -0.53
    তথ্যসূত্র
    -0.53
    //
    -0.53
    POSITIVE LOGITS
     aesthetically
    2.01
     aesthetic
    1.97
     aesthetics
    1.93
     beauty
    1.83
     beautiful
    1.74
     Aesthetic
    1.68
    aesthetic
    1.67
    beautiful
    1.66
    Aesthetic
    1.66
     Beautiful
    1.66
    Activations Density 0.503%

    No Known Activations