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

    Neuronpedia

    APICircuit 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. 0-GEMMASCOPE-RES-16K
    6. 8184
    Prev
    Next
    INDEX
    Explanations

    import statements in code and references to prices or currency-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <<<<<<<<<<<<<<
    -0.58
     المعيارى
    -0.58
    ulturally
    -0.55
    MenuInflater
    -0.55
     murales
    -0.54
    orianCalendar
    -0.53
    intellij
    -0.51
     crisi
    -0.51
    대한
    -0.50
    othelioma
    -0.50
    POSITIVE LOGITS
    JspWriter
    0.74
     Eſ
    0.71
     Оно
    0.63
     transfieras
    0.63
    zzleHttp
    0.62
    UnitTesting
    0.60
    [:]
    0.60
     relationship
    0.60
    υτό
    0.57
     ब्रेकडाउन
    0.57
    Activations Density 0.201%

    No Known Activations