© 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. 1570
    Prev
    Next
    INDEX
    Explanations

    references to specific names, particularly related to individuals or cultural terms

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

    "vi" followed by other letters

    np_acts-logits-general · gemini-2.0-flash

    words starting with vi or wi

    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
    addPreferredGap
    -0.63
    neux
    -0.61
     Mexique
    -0.54
     heaven
    -0.54
     کرده
    -0.52
    llon
    -0.51
    Rien
    -0.51
     Burrell
    -0.50
     contribution
    -0.50
     Mullen
    -0.50
    POSITIVE LOGITS
     Wis
    0.80
     Wib
    0.76
    Wis
    0.73
     Vict
    0.72
     تضيفلها
    0.70
    Wit
    0.69
     Wiz
    0.68
     wi
    0.66
     Wit
    0.66
     WIT
    0.65
    Activations Density 0.118%

    No Known Activations