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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3781
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of people and places

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

    followed by names

    np_acts-logits-general · gemini-2.0-flash

    names followed by surnames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     réfé
    -0.43
     Saúde
    -0.43
     Walther
    -0.41
    angkut
    -0.40
     svå
    -0.40
     Umum
    -0.39
     Perdana
    -0.38
     Hitam
    -0.38
     redonda
    -0.38
     Stimm
    -0.38
    POSITIVE LOGITS
     Zr
    0.79
     laſſen
    0.68
    PageRoute
    0.66
     թվական
    0.64
     Alias
    0.63
     Loft
    0.63
     Juliette
    0.63
    oa̍t
    0.62
    ThroughAttribute
    0.61
     Gild
    0.61
    Activations Density 2.092%

    No Known Activations