© 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. 14288
    Prev
    Next
    INDEX
    Explanations

    references to medical facilities and healthcare services

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

    Prepositions "at" and "to" preceding locations/institutions

    np_acts-logits-general · gemini-2.0-flash

    locations of hospitals and universities

    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
    AndEndTag
    -0.57
    terase
    -0.54
     SwitchCompat
    -0.53
    SwitchCompat
    -0.49
    ودة
    -0.48
    djangoproject
    -0.47
     blindly
    -0.45
    able
    -0.44
    PreInfinity
    -0.43
     bParam
    -0.43
    POSITIVE LOGITS
    脚注の使い方
    0.71
     Mercy
    0.68
    VIAF
    0.66
     autorytatywna
    0.63
     Methodist
    0.62
    InvalidProtocol
    0.62
    DockStyle
    0.61
     disambiguazione
    0.60
     Franciscan
    0.59
     SSM
    0.59
    Activations Density 0.123%

    No Known Activations