© 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. 8789
    Prev
    Next
    INDEX
    Explanations

    strengths and positive attributes of a product or service

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

    Follows commas in foreign language text

    np_acts-logits-general · gemini-2.0-flash

    numerical sequences

    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
     relâche
    -0.60
    parseDouble
    -0.51
     Ibid
    -0.51
    исленность
    -0.50
    Stayed
    -0.50
    ingdon
    -0.50
     typeof
    -0.49
    typeof
    -0.48
     neither
    -0.48
     INTERPRET
    -0.48
    POSITIVE LOGITS
    :✨
    0.97
    Carriera
    0.74
    
    0.72
     Fits
    0.66
     fits
    0.63
     تكبرها
    0.58
     MainAxisSize
    0.57
     Convenient
    0.56
     convenient
    0.56
    Chham
    0.56
    Activations Density 0.003%

    No Known Activations