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. 20-GEMMASCOPE-RES-16K
    6. 9387
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and relational objections, disputes, and classifications

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

    Preceding words indicating generality or overstatements

    np_acts-logits-general · gemini-2.0-flash

    general or broad

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndInit
    -1.00
    endphp
    -0.90
    BeginInit
    -0.78
    IUrlHelper
    -0.73
     <>",
    -0.72
     Efq
    -0.72
    setVerticalGroup
    -0.70
    HomeAsUpEnabled
    -0.70
     Chriftian
    -0.69
     ModelExpression
    -0.67
    POSITIVE LOGITS
     general
    2.27
    general
    1.95
     generic
    1.78
     GENERAL
    1.72
     generalized
    1.68
     algemene
    1.67
    General
    1.64
     général
    1.64
     generale
    1.63
     broad
    1.61
    Activations Density 0.889%

    No Known Activations