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. 16-GEMMASCOPE-RES-16K
    6. 54
    Prev
    Next
    INDEX
    Explanations

    references to file handling and operating system operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Imports in Java/Kotlin/Android code

    np_acts-logits-general · gemini-2.0-flash

    file I/O and serialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gesetzt
    -0.51
    unched
    -0.48
     Paris
    -0.48
     popularity
    -0.47
     flo
    -0.46
     al
    -0.46
     green
    -0.45
    ző
    -0.44
     nu
    -0.44
     éxitos
    -0.44
    POSITIVE LOGITS
     متعلقه
    1.19
    ThroughAttribute
    0.99
     contextLoads
    0.92
    ItemBackground
    0.91
    findpost
    0.89
    awaiter
    0.88
    TypedDataSet
    0.87
    CloseOperation
    0.86
     protoimpl
    0.86
     виправивши
    0.86
    Activations Density 0.032%

    No Known Activations