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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 12656
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting elements in text

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

    Code snippets with brackets and symbols

    np_acts-logits-general · gemini-2.0-flash

    code block endings and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ↵
    -1.05
    PyExc
    -0.45
     ſame
    -0.45
     coexistence
    -0.44
    ↵↵↵
    -0.43
    $.\\
    -0.43
     prie
    -0.43
    }$\\
    -0.43
    .*;
    -0.43
    .$
    -0.43
    POSITIVE LOGITS
    ↵↵
    0.96
    '},
    
    0.83
    '):
    
    0.82
    "):
    
    0.78
    expandindo
    0.75
    ")]
    
    0.74
    ');
    
    0.70
    )");
    
    0.70
    )";
    
    0.69
    principalColumn
    0.68
    Activations Density 0.082%

    No Known Activations