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. 7485
    Prev
    Next
    INDEX
    Explanations

    opening curly braces in code or structured text

    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
    ize
    -0.60
    ipal
    -0.59
     works
    -0.57
     lòng
    -0.56
     beng
    -0.55
    بوابة
    -0.55
     lượng
    -0.54
     bent
    -0.53
    üyada
    -0.53
     mel
    -0.52
    POSITIVE LOGITS
    ↵
    0.85
     };
    0.77
    ChromeDriver
    0.75
    GEBURTSDATUM
    0.74
    }))
    0.72
     }
    0.72
    __":
    
    0.70
    RenderAtEndOf
    0.69
    });
    
    0.69
    ↵↵
    0.67
    Activations Density 0.090%

    No Known Activations