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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7340
    Prev
    Next
    INDEX
    Explanations

    code patterns related to data fetching and asynchronous operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ScopeManager
    -0.60
                                  
    -0.48
     FishBase
    -0.48
    famille
    -0.48
     xrange
    -0.47
     ویکی‌پدیا
    -0.47
    PasswordEncoder
    -0.46
    /*++
    -0.46
     FANDOM
    -0.46
    kpop
    -0.46
    POSITIVE LOGITS
    ValueStyle
    0.70
     correctes
    0.63
    !*\
    0.63
    Hochspringen
    0.62
    }*/
    
    0.61
    RenderAtEndOf
    0.59
     HasFactory
    0.58
     Afterward
    0.58
     "}
    0.57
    });*/
    0.56
    Activations Density 0.022%

    No Known Activations