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. 15-GEMMASCOPE-RES-16K
    6. 5102
    Prev
    Next
    INDEX
    Explanations

    code structures and syntax related to function definitions and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Przypisy
    -0.62
    ..
    -0.48
    lu
    -0.45
    BagConstraints
    -0.44
    state
    -0.44
     viewType
    -0.43
    ...
    -0.43
    li
    -0.43
    je
    -0.42
     Models
    -0.42
    POSITIVE LOGITS
    RectangleBorder
    0.91
     Majefty
    0.73
    WithMany
    0.72
    kháu
    0.70
    انيف
    0.70
    Portály
    0.68
     itſelf
    0.68
     متعلقه
    0.66
    ipelago
    0.66
     Jefus
    0.64
    Activations Density 0.242%

    No Known Activations