© 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. 4-GEMMASCOPE-RES-16K
    11. 3630
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "was" and its various conjugations or related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.83
    AddTagHelper
    -0.78
    Билгалдахарш
    -0.78
    الحياه
    -0.76
    tagHelperRunner
    -0.75
    Hentet
    -0.72
     незавершена
    -0.70
    GEBURTSDATUM
    -0.69
     humaine
    -0.69
     umana
    -0.68
    POSITIVE LOGITS
    Datuak
    0.60
     think
    0.60
    gesteld
    0.57
    หวัด
    0.54
    oide
    0.52
    étais
    0.48
    ే
    0.47
     Was
    0.47
    tuta
    0.47
     thought
    0.46
    Activations Density 0.172%

    No Known Activations