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. 14-GEMMASCOPE-RES-16K
    6. 275
    Prev
    Next
    INDEX
    Explanations

    Python code constructs and programming-related elements, particularly related to data structures and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.83
     parseFrom
    -0.67
    Lähteet
    -0.66
    Personensuche
    -0.63
    UserScript
    -0.62
    Šaltiniai
    -0.61
    ANTLR
    -0.61
    __":
    
    -0.61
    DataAnnotations
    -0.61
    )‏
    -0.60
    POSITIVE LOGITS
     thép
    0.47
    chyma
    0.47
    ianum
    0.45
     unregistered
    0.44
    جموع
    0.42
    ossa
    0.42
    וי
    0.42
    estial
    0.42
    AspNet
    0.42
    aughan
    0.41
    Activations Density 1.057%

    No Known Activations