© 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. 23-GEMMASCOPE-RES-16K
    11. 14507
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "was" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bientôt
    -0.67
     désormais
    -0.63
     asemenea
    -0.61
    ValueStyle
    -0.58
    UnitTesting
    -0.58
    كويكب
    -0.57
     fortfarande
    -0.56
     maintenant
    -0.55
    now
    -0.54
     теперь
    -0.53
    POSITIVE LOGITS
     originally
    0.96
     born
    0.92
     recently
    0.85
     formerly
    0.84
     previously
    0.80
    rrggbb
    0.80
     ursprünglich
    0.77
     once
    0.73
     originalmente
    0.73
    originally
    0.72
    Activations Density 0.234%

    No Known Activations