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. 2098
    Prev
    Next
    INDEX
    Explanations

    JSON syntax elements and structure

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

    "Sixth" or "six" (variants and misspellings)

    np_acts-logits-general · gemini-2.0-flash

    six or 6

    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
     dimanche
    -0.50
     domenica
    -0.49
     terça
    -0.48
    spre
    -0.47
     martes
    -0.47
    Atoi
    -0.46
    NSMutable
    -0.46
    Dimanche
    -0.46
     MARTIN
    -0.46
     Sunday
    -0.46
    POSITIVE LOGITS
          
    1.10
     sixth
    0.97
     Sixth
    0.91
    Sixth
    0.87
    6
    0.86
    sixth
    0.86
     Six
    0.84
     SIX
    0.83
    第六
    0.79
     six
    0.79
    Activations Density 0.117%

    No Known Activations