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 - 131k
    5. 33-GEMMASCOPE-RES-131K
    6. 65790
    Prev
    Next
    INDEX
    Explanations

    references to a specific person named Ralph

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_131k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.60
     Paglinawan
    -0.55
     estekak
    -0.52
     kasarigan
    -0.49
    AndEndTag
    -0.46
    SharedDtor
    -0.45
    Revenir
    -0.44
    IANGLES
    -0.44
    TagMode
    -0.43
     operativos
    -0.42
    POSITIVE LOGITS
     Ralph
    0.60
     ralph
    0.60
    ralph
    0.56
     Lauren
    0.54
    Ralph
    0.51
     Waldo
    0.49
     lauren
    0.49
    lauren
    0.49
    alph
    0.45
     RALPH
    0.45
    Activations Density 0.004%

    No Known Activations