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. 17-GEMMASCOPE-RES-16K
    6. 1210
    Prev
    Next
    INDEX
    Explanations

    references to the concept of Satan or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    帖最后由
    -0.68
    lső
    -0.50
    libft
    -0.47
     AssemblyProduct
    -0.47
     Pearce
    -0.45
    adpleegd
    -0.45
     ‘
    -0.45
    Timo
    -0.45
    himp
    -0.44
     أع
    -0.44
    POSITIVE LOGITS
     للمعارف
    1.04
     SAT
    0.97
     Saty
    0.96
    IsContent
    0.84
    SAT
    0.78
    homonymie
    0.75
    хьтан
    0.74
     Sat
    0.71
     Sati
    0.69
     Satt
    0.68
    Activations Density 0.165%

    No Known Activations