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. 11-GEMMASCOPE-RES-16K
    6. 6112
    Prev
    Next
    INDEX
    Explanations

    specific parts and components related to bicycles, particularly the crank and bottom bracket system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )))));
    -0.54
    ]));
    
    -0.53
    =""></
    -0.53
    hagy
    -0.52
    ///**
    -0.51
     ').
    -0.50
     تضيفلها
    -0.49
    ]),
    
    -0.49
     robust
    -0.49
     robus
    -0.49
    POSITIVE LOGITS
     fevere
    0.68
     ſever
    0.64
     houſe
    0.63
     NSCoder
    0.62
     purpoſe
    0.61
     Jefus
    0.60
     pleaſure
    0.59
     ſte
    0.59
     Houſe
    0.59
     ſche
    0.58
    Activations Density 0.387%

    No Known Activations