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. 31-GEMMASCOPE-RES-16K
    6. 16004
    Prev
    Next
    INDEX
    Explanations

    phrases related to lunches brought from home

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

    Sentences containing the word "bring" or "brought"

    np_acts-logits-general · gemini-2.0-flash

    bring, brought, carry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VolleyError
    -0.40
    TagMode
    -0.40
    scalatest
    -0.38
    ➟
    -0.35
    Seeder
    -0.33
    mio
    -0.33
     تضيفلها
    -0.32
    #+#
    -0.32
    ofire
    -0.32
    drawString
    -0.32
    POSITIVE LOGITS
     Bring
    2.02
    Bring
    2.02
     bring
    1.97
    bring
    1.91
     bringing
    1.79
     BRING
    1.74
     brought
    1.73
     brings
    1.70
    bringing
    1.66
    brought
    1.63
    Activations Density 0.138%

    No Known Activations