Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 12756
    Prev
    Next
    INDEX
    Explanations

    mentions of specific months and dates

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

    Months of the year

    np_acts-logits-general · gemini-2.0-flash

    months in dates

    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
    انيف
    -0.63
     فريبيس
    -0.55
     <<<<<<<<<<<<<<
    -0.50
    Personensuche
    -0.50
    typeof
    -0.50
     OMITBAD
    -0.49
    ercito
    -0.46
    Diweddarwch
    -0.45
    日目
    -0.44
    исленность
    -0.44
    POSITIVE LOGITS
    TagMode
    0.80
     fevere
    0.74
     betweenstory
    0.73
    rungsseite
    0.71
    CloseOperation
    0.70
     Monfieur
    0.70
     Efq
    0.69
     uſed
    0.69
     ſche
    0.67
     XNUMX
    0.67
    Activations Density 0.099%

    No Known Activations