© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 9548
    Prev
    Next
    INDEX
    Explanations

    proper nouns and titles, particularly those related to places and people

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

    Follows capitalized words or names

    np_acts-logits-general · gemini-2.0-flash

    Jon Lee, Atlantic City, Miami Bel

    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
     Phoebe
    -0.76
    UnknownFields
    -0.74
     Barrie
    -0.67
     []:
    -0.63
    äude
    -0.62
    Phoebe
    -0.62
     farma
    -0.60
     nakalista
    -0.58
     Craw
    -0.58
     Zjednoc
    -0.57
    POSITIVE LOGITS
     Stedman
    0.83
    lename
    0.82
     Essex
    0.74
    AsUp
    0.74
     Wiktionnaire
    0.72
     Mercier
    0.70
     Hecht
    0.68
    DBNull
    0.68
    Essex
    0.68
    spells
    0.68
    Activations Density 0.544%

    No Known Activations