© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 1317
    Prev
    Next
    INDEX
    Explanations

    the word "much" and its various forms or contexts in relation to quantity or degree

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Бахар
    -0.81
     AssemblyTitle
    -0.74
     ProtoMessage
    -0.70
    expandindo
    -0.69
    jspx
    -0.68
     GenerationType
    -0.62
    rawDesc
    -0.61
     AssemblyProduct
    -0.60
     ComVisible
    -0.60
     Efq
    -0.60
    POSITIVE LOGITS
     ado
    0.88
    ísimas
    0.73
    needed
    0.70
     needed
    0.68
     Ado
    0.67
     larger
    0.61
     easier
    0.59
     like
    0.59
     appreciated
    0.59
     worse
    0.57
    Activations Density 0.118%

    No Known Activations