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. 1683
    Prev
    Next
    INDEX
    Explanations

    specific words that relate to prepositions and conjunctions in various languages

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

    Prefixes of words in various languages

    np_acts-logits-general · gemini-2.0-flash

    word beginnings

    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
    Síguenos
    -0.67
    __':
    
    -0.67
    EndGlobalSection
    -0.66
    sidemargin
    -0.65
     незавершена
    -0.65
    DockStyle
    -0.63
    __":
    
    -0.62
    __":
    -0.61
    NUMX
    -0.59
    RetentionPolicy
    -0.58
    POSITIVE LOGITS
     Kopf
    0.59
    plat
    0.56
    差
    0.55
    WR
    0.55
    mas
    0.54
    ras
    0.53
    го
    0.52
    tra
    0.51
    մ
    0.51
    TR
    0.51
    Activations Density 0.027%

    No Known Activations