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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10719
    Prev
    Next
    INDEX
    Explanations

    phrases related to service-oriented businesses and local establishments

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

    Comes before a name or company

    np_acts-logits-general · gemini-2.0-flash

    calling or hiring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     Fifa
    -0.64
     ArcGIS
    -0.64
     FIFA
    -0.63
     MusicBrainz
    -0.62
    FIFA
    -0.61
     LEGO
    -0.60
     UNAM
    -0.60
    UEFA
    -0.60
    LEGO
    -0.59
     UEFA
    -0.59
    POSITIVE LOGITS
    NUMX
    0.68
    ㈱
    0.68
    ㈲
    0.65
    pacific
    0.61
    株式会社
    0.59
     Pacific
    0.58
     Valley
    0.57
     The
    0.56
     Elite
    0.56
    ✨:
    0.56
    Activations Density 0.315%

    No Known Activations