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. 8654
    Prev
    Next
    INDEX
    Explanations

    terms related to epidemiology and environmental factors affecting pathogens

    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
    MigrationBuilder
    -0.97
    Personendaten
    -0.91
     ProtoMessage
    -0.85
     تضيفلها
    -0.80
    CppMethod
    -0.79
     يتيمه
    -0.77
     архивлан
    -0.77
    DebuggerNonUser
    -0.77
    SharedDtor
    -0.76
     Administrativna
    -0.76
    POSITIVE LOGITS
     (
    0.52
     of
    0.50
    emf
    0.45
     with
    0.45
     like
    0.43
     in
    0.43
     without
    0.41
     option
    0.39
     status
    0.39
     on
    0.38
    Activations Density 3.806%

    No Known Activations