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. 5-GEMMASCOPE-RES-16K
    6. 11734
    Prev
    Next
    INDEX
    Explanations

    programming language import statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kování
    -0.59
     numberWith
    -0.57
    +#+
    -0.55
    レスト
    -0.55
    tagHelper
    -0.55
    SWIG
    -0.53
    ScopeManager
    -0.52
    ControllerAdvice
    -0.52
    nosť
    -0.52
    hauser
    -0.52
    POSITIVE LOGITS
    ]');
    1.13
    )');
    1.09
    ]]);
    1.08
    `;
    
    1.08
    '});
    1.05
    >>();
    1.03
    ';
    
    1.03
    })();
    
    1.01
    ')));
    1.01
    '));
    1.01
    Activations Density 0.023%

    No Known Activations