© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 16210
    Prev
    Next
    INDEX
    Explanations

    key terms related to health professions and career-related services

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

    before academic departments or roles

    np_acts-logits-general · gemini-2.0-flash

    university and college administration

    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
    djangoproject
    -0.78
    EDEFAULT
    -0.61
     YOUTH
    -0.58
     disambiguazione
    -0.57
     Wikimedijinoj
    -0.57
    siąż
    -0.57
     estimés
    -0.57
     youth
    -0.57
    charity
    -0.56
     Савезне
    -0.55
    POSITIVE LOGITS
     Provost
    0.94
     faculty
    0.92
     provo
    0.83
     Faculty
    0.79
     dean
    0.73
    Faculty
    0.72
     campus
    0.71
     Athletics
    0.70
    faculty
    0.69
     Advis
    0.69
    Activations Density 0.197%

    No Known Activations