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. 3-GEMMASCOPE-RES-16K
    6. 10954
    Prev
    Next
    INDEX
    Explanations

    Java output methods and associated print statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enfans
    -0.78
    }*/
    
    -0.73
    })->
    -0.73
    出版年
    -0.69
     igång
    -0.68
     geïsole
    -0.67
    hasilkan
    -0.66
     **/
    
    -0.65
     beſt
    -0.65
     fidé
    -0.64
    POSITIVE LOGITS
    OrWhiteSpace
    0.96
    URIComponent
    0.91
    Sprintf
    0.80
    PrototypeOf
    0.80
    ForResult
    0.79
    AddWithValue
    0.74
    WidgetItem
    0.69
     AssemblyTitle
    0.68
    ,
    0.67
    ↵
    0.65
    Activations Density 0.085%

    No Known Activations