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. 2889
    Prev
    Next
    INDEX
    Explanations

    punctuations and specific symbols

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

    contrast or concession

    np_acts-logits-general · gemini-2.0-flash

    conjunctions and separators

    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
     welcher
    -0.60
     welches
    -0.53
    ?”,
    -0.53
    EUROPA
    -0.52
     welche
    -0.52
     hierbei
    -0.52
    anasia
    -0.51
    zzleHttp
    -0.50
    SourceChecksum
    -0.49
    ude
    -0.49
    POSITIVE LOGITS
     though
    1.03
     although
    1.02
    though
    0.87
     choć
    0.81
    although
    0.80
     embora
    0.80
    indeed
    0.79
     zumal
    0.79
     quoique
    0.78
     indeed
    0.77
    Activations Density 0.482%

    No Known Activations