Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 24-GEMMASCOPE-RES-16K
    6. 2242
    Prev
    Next
    INDEX
    Explanations

    phrases relating to organizational structure and responsibilities within the industry

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

    Trade associations or industry bodies

    np_acts-logits-general · gemini-2.0-flash

    trade associations and unions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی
    -0.54
     progetti
    -0.51
    chiere
    -0.50
    Mitarbeiter
    -0.50
    getTeam
    -0.49
    WebServlet
    -0.48
     kine
    -0.47
    kmale
    -0.46
    opardy
    -0.46
    στη
    -0.45
    POSITIVE LOGITS
     association
    1.62
     associations
    1.47
     Association
    1.45
    Association
    1.38
    association
    1.35
     Associations
    1.31
     ASSOCIATION
    1.27
    Associations
    1.17
    associations
    1.17
     industry
    1.11
    Activations Density 0.143%

    No Known Activations