Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 14559
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and their usage in context

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

    Follows pronoun/noun, precedes verb

    np_acts-logits-general · gemini-2.0-flash

    linking clauses

    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
     sice
    -0.79
     therefore
    -0.75
     infatti
    -0.73
     zwar
    -0.73
    therefore
    -0.71
    thus
    -0.66
    λοι
    -0.58
     thus
    -0.57
    indeed
    -0.56
     hence
    -0.55
    POSITIVE LOGITS
     ändå
    1.15
     nonetheless
    1.12
     nevertheless
    1.09
    卻
    1.03
     trotzdem
    1.02
    却
    1.02
     digress
    1.00
     dennoch
    1.00
    却没有
    0.97
    却是
    0.97
    Activations Density 0.704%

    No Known Activations