© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 5753
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to engineering and mechanics

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

    Comes after "electric", "pass", or "motor"

    np_acts-logits-general · gemini-2.0-flash

    electric motor, pass transistor, fatty acid synthase

    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
     المعيارى
    -0.60
    ьаж
    -0.56
     الحره
    -0.54
     femenina
    -0.52
    TypedDataSet
    -0.50
    女士
    -0.47
     bint
    -0.45
    DataSnapshot
    -0.44
    sság
    -0.43
    druk
    -0.42
    POSITIVE LOGITS
    __':
    
    1.03
    __":
    
    0.88
     متعلقه
    0.79
     useRouter
    0.72
    __':
    0.71
    ChromeDriver
    0.68
     onOptions
    0.67
    دانشنامهٔ
    0.65
     FontWeight
    0.65
    }));
    
    0.64
    Activations Density 8.124%

    No Known Activations