© 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. 3351
    Prev
    Next
    INDEX
    Explanations

    repeated phrases or uses of the word "to."

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

    Comes before an infinitive verb

    np_acts-logits-general · gemini-2.0-flash

    to verb

    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
     habet
    -0.71
     venait
    -0.70
     Jefus
    -0.70
    able
    -0.68
     căr
    -0.63
     Chriftian
    -0.63
     endeavouring
    -0.63
     poffible
    -0.63
     Efq
    -0.63
     pidiendo
    -0.61
    POSITIVE LOGITS
     be
    1.49
     make
    1.01
     have
    0.99
     become
    0.91
     take
    0.90
     see
    0.90
     give
    0.89
    MENAFN
    0.88
     keep
    0.86
     bring
    0.85
    Activations Density 0.784%

    No Known Activations