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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 53
    Prev
    Next
    INDEX
    Explanations

    references to well-known personalities and their interactions

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

    names of notable or famous individuals and celebrities.

    oai_token-act-pair · gpt-4oTriggered by @neilrathi

    names and celebrity-related references.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    ChildScrollView
    -0.61
    transQ
    -0.60
    enterOuterAlt
    -0.57
    heça
    -0.56
    webElementXpaths
    -0.53
    errHandler
    -0.52
    IntoConstraints
    -0.50
    endphp
    -0.49
    RenderAtEndOf
    -0.48
     purpoſe
    -0.48
    POSITIVE LOGITS
     celebrities
    0.66
     celebrity
    0.54
     celebs
    0.49
     eminent
    0.45
     celebridades
    0.44
     ünl
    0.42
     يتيمه
    0.41
     Nobel
    0.41
     illustrious
    0.41
    celebrity
    0.41
    Activations Density 0.191%

    No Known Activations