© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 5816
    Prev
    Next
    INDEX
    Explanations

    occurrences of code blocks and structural elements like classes, methods, and functions within programming-related text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     IBOutlet
    -0.76
     littéraire
    -0.70
     Jahr
    -0.62
     démo
    -0.60
     Goliath
    -0.59
     Bouch
    -0.58
     Saludos
    -0.56
    jfree
    -0.55
     Lese
    -0.55
     randomNumber
    -0.55
    POSITIVE LOGITS
    GEBURTSDATUM
    0.86
    
    0.73
    riwal
    0.70
    herjee
    0.69
    enchymal
    0.69
    dymyr
    0.69
    IZONTAL
    0.69
    melse
    0.65
    ंदीखरीदारी
    0.65
    odyear
    0.65
    Activations Density 0.086%

    No Known Activations