Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9306
    Prev
    Next
    INDEX
    Explanations

    detailed descriptions and measurements related to physical materials and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.78
    Datuak
    -0.69
    Хьажоргаш
    -0.64
     referenties
    -0.60
     تضيفلها
    -0.57
    itory
    -0.57
    })));
    -0.57
     ivelany
    -0.56
    Chham
    -0.56
     Ganz
    -0.55
    POSITIVE LOGITS
     thickness
    2.20
     thick
    1.89
     Thickness
    1.85
     thicknesses
    1.81
    thickness
    1.78
     thicker
    1.78
    Thickness
    1.72
     Thick
    1.68
    thick
    1.68
    Thick
    1.64
    Activations Density 0.374%

    No Known Activations