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. 5-GEMMASCOPE-RES-16K
    6. 2621
    Prev
    Next
    INDEX
    Explanations

    references to spiritual or mystical practices and beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -1.13
     '\\;'
    -1.02
    writeFieldEnd
    -1.00
     cherchés
    -0.98
     Baillargeon
    -0.98
     kasarigan
    -0.97
     nahilalakip
    -0.95
     myſelf
    -0.93
    principalColumn
    -0.92
    Tikang
    -0.92
    POSITIVE LOGITS
    "
    0.55
     n
    0.53
     ent
    0.51
     "
    0.51
     array
    0.50
     op
    0.48
     and
    0.47
     m
    0.47
     material
    0.47
    !"
    0.46
    Activations Density 0.228%

    No Known Activations