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. 16049
    Prev
    Next
    INDEX
    Explanations

    code-related structures and labels, particularly in programming or technical documentation

    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
    ]";
    -0.88
     }}$}
    -0.85
    });*/
    -0.82
    };*/
    -0.81
    %";
    -0.81
    "]);
    
    -0.81
    )";
    
    -0.80
    )";
    -0.78
    .";
    
    -0.77
    "});
    -0.77
    POSITIVE LOGITS
    ScopeManager
    0.64
    ActionPerformed
    0.61
    RegressionTest
    0.60
    󠁴
    0.59
     Read
    0.54
    +:+
    0.53
     編
    0.53
     imagePath
    0.53
     Edit
    0.52
    Hochspringen
    0.52
    Activations Density 1.747%

    No Known Activations