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. 20-GEMMASCOPE-RES-16K
    6. 5381
    Prev
    Next
    INDEX
    Explanations

    terms related to specific physical components and their interactions in mechanical and electrical systems

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

    Plural nouns, often technical or scientific

    np_acts-logits-general · gemini-2.0-flash

    possessive components in multiple languages

    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
    WriteTagHelper
    -1.00
    :✨
    -0.97
    脚注の使い方
    -0.90
     its
    -0.90
     مشين
    -0.85
    Tembelea
    -0.84
    EndGlobalSection
    -0.84
    MLLoader
    -0.83
     Its
    -0.82
    Its
    -0.81
    POSITIVE LOGITS
     themselves
    0.95
    Their
    0.86
     their
    0.75
     Their
    0.70
    their
    0.69
    themselves
    0.69
     ihre
    0.53
     stessi
    0.50
     THEIR
    0.50
     دیکھیے
    0.47
    Activations Density 1.110%

    No Known Activations