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. 1243
    Prev
    Next
    INDEX
    Explanations

    references to specific actions or features related to software updates or app functionalities

    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
    achsen
    -0.63
    jetty
    -0.60
     turísticos
    -0.56
     Herrmann
    -0.56
    arita
    -0.56
     Nag
    -0.55
    rington
    -0.55
    ябре
    -0.54
    hintText
    -0.54
    age
    -0.54
    POSITIVE LOGITS
    */
    
    
    0.92
     }}$}
    0.88
    };*/
    0.85
    [])
    
    0.84
    ']))
    
    0.84
    );
    
    
    0.81
     Normdatei
    0.79
    });
    
    
    0.79
    ();*/
    0.78
    })*/
    0.78
    Activations Density 0.032%

    No Known Activations