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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-GEMMASCOPE-RES-16K
    6. 13217
    Prev
    Next
    INDEX
    Explanations

    declarations of public and private access modifiers in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ligiloj
    -0.84
     Administrativna
    -0.80
     فريبيس
    -0.72
     Италијани
    -0.63
    EClass
    -0.62
     betweenstory
    -0.61
    daq
    -0.60
    IsMutable
    -0.60
    LookAnd
    -0.58
    gnore
    -0.58
    POSITIVE LOGITS
    public
    0.95
     }}"></
    0.74
     IBOutlet
    0.74
    IMPORTED
    0.73
    )");
    
    0.69
    ")));
    
    0.68
    "):
    
    0.68
     }}$}
    0.66
     kran
    0.66
    ¹)
    0.65
    Activations Density 0.030%

    No Known Activations