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. 15759
    Prev
    Next
    INDEX
    Explanations

    terms related to reception and visitor interaction in a service context

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

    a "receptionist" or "reception"

    np_acts-logits-general · gemini-2.0-flash

    receptionist or reception desk

    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
    TagMode
    -0.60
     vPvB
    -0.57
     kasarigan
    -0.57
    glEnd
    -0.56
    Rüyada
    -0.56
    endphp
    -0.54
    UnitTesting
    -0.51
     незавершена
    -0.49
     <>",
    -0.49
    aragus
    -0.48
    POSITIVE LOGITS
     receptionist
    1.19
     reception
    1.18
    reception
    1.08
     Reception
    1.05
     desk
    1.00
    Reception
    0.97
     Empfang
    0.93
     recepción
    0.84
    受付
    0.83
     lobby
    0.81
    Activations Density 0.050%

    No Known Activations