© 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. 18-GEMMASCOPE-RES-16K
    11. 3951
    Prev
    Next
    INDEX
    Explanations

    references to quantities or counts, particularly those expressed in plural forms

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

    Numbers expressed as words

    np_acts-logits-general · gemini-2.0-flash

    numbers quantifying nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     âmes
    -0.72
     flera
    -0.65
     flere
    -0.64
     chrétiens
    -0.61
     mères
    -0.61
    another
    -0.59
     blessés
    -0.58
     kaikk
    -0.57
     genoux
    -0.57
     altres
    -0.57
    POSITIVE LOGITS
     Roskov
    0.90
     remaining
    0.87
     closest
    0.80
     largest
    0.77
     longest
    0.76
    remaining
    0.76
    iniest
    0.75
    liest
    0.74
     aforementioned
    0.74
     oldest
    0.73
    Activations Density 0.213%

    No Known Activations