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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9799
    Prev
    Next
    INDEX
    Explanations

    terms associated with religious or spiritual figures.

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

    aspects and instructions related to religious worship and rituals.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    numbered list items or enumerated points in text.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot
    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
    parsedMessage
    -0.55
    السكان
    -0.51
    SharedDtor
    -0.48
    encodeWith
    -0.48
    WithIOException
    -0.47
    PathVariable
    -0.44
    Lähteet
    -0.43
    \
    -0.43
    $__
    -0.43
    webElementXpaths
    -0.43
    POSITIVE LOGITS
    Autoritní
    0.70
     الحره
    0.68
    Personensuche
    0.67
    covo
    0.62
     wikipagina
    0.59
    ècie
    0.58
     circums
    0.56
     vectorstock
    0.56
    findpost
    0.55
     auras
    0.55
    Activations Density 0.055%

    No Known Activations