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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2863
    Prev
    Next
    INDEX
    Explanations

    concepts related to social dynamics and collaborative efforts.

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

    patterns related to manufacturing processes and sustainability initiatives.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    nouns related to abstract concepts or professional activities, particularly in business, legal, and social contexts.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered 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
    /
    -0.82
    -/
    -0.75
    /
    -0.69
     '/';
    -0.68
    /
    
    -0.67
     /
    -0.64
     "/";
    -0.64
    /');
    -0.61
    $/
    -0.61
    hyrchwyd
    -0.61
    POSITIVE LOGITS
     etc
    1.08
    etc
    0.83
     usw
    0.81
    migrationBuilder
    0.74
     Etc
    0.72
     stb
    0.72
    +#+#
    0.72
    ともに
    0.71
     등
    0.70
     ועוד
    0.69
    Activations Density 0.543%

    No Known Activations