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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 12421
    Prev
    Next
    INDEX
    Explanations

    parts of a structured data format or metadata indicators

    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
    ()));
    
    -0.49
    Loading
    -0.47
    ()};
    -0.47
    ++);
    -0.44
    bula
    -0.44
    meanor
    -0.43
    ұ
    -0.43
    ++;
    
    -0.43
    ++]
    -0.42
    '))
    
    -0.42
    POSITIVE LOGITS
     disambiguazione
    0.82
    gnore
    0.80
    CardContent
    0.76
     препратки
    0.76
    IntoConstraints
    0.71
    chengladbach
    0.70
    WidgetItem
    0.69
     inplace
    0.69
    jetunion
    0.67
    medriver
    0.66
    Activations Density 0.441%

    No Known Activations