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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 4645
    Prev
    Next
    INDEX
    Explanations

    conditional statements and variable declarations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     useStyles
    -0.61
     suivez
    -0.58
    ViewImports
    -0.58
    iniums
    -0.57
    存于互联网档案馆
    -0.56
    RunWith
    -0.56
    digarh
    -0.55
    aktur
    -0.55
     linkovi
    -0.55
    toThrow
    -0.54
    POSITIVE LOGITS
     кӀ
    0.52
    upol
    0.52
    atguigu
    0.50
    NullCheck
    0.49
    +)/
    0.48
    แจ
    0.48
    ichthys
    0.48
    `;
    
    0.48
    تقاوى
    0.48
     acaso
    0.47
    Activations Density 0.087%

    No Known Activations