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. 16-GEMMASCOPE-RES-16K
    6. 1504
    Prev
    Next
    INDEX
    Explanations

    code associated with classes and methods in programming

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

    Code snippets with type declarations or math expressions

    np_acts-logits-general · gemini-2.0-flash

    void method calls

    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
    tonsoft
    -0.57
     références
    -0.56
    verwijspagina
    -0.55
     Gobernador
    -0.55
     sendiri
    -0.52
    يكب
    -0.52
    Desta
    -0.52
    новниш
    -0.52
    iastes
    -0.52
    ösung
    -0.52
    POSITIVE LOGITS
    WebVitals
    0.61
     department
    0.56
     books
    0.55
    routeProvider
    0.55
    صف
    0.54
     Books
    0.52
    //
    0.51
    #+#
    0.50
    BufferException
    0.49
    sizeCache
    0.49
    Activations Density 0.211%

    No Known Activations