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. 24-GEMMASCOPE-RES-16K
    6. 12715
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to towns and geographic locations

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

    Locations or place names

    np_acts-logits-general · gemini-2.0-flash

    place names and associated regions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oplayer
    -0.61
    jahtera
    -0.56
    ControllerAdvice
    -0.54
    chutz
    -0.54
    Inflater
    -0.53
     "}";
    -0.51
    rawDesc
    -0.50
     >=",
    -0.50
     <>",
    -0.49
    kusen
    -0.49
    POSITIVE LOGITS
     Area
    0.75
     resident
    0.74
     High
    0.73
     Chamber
    0.68
     residents
    0.64
     Rotary
    0.64
     native
    0.63
     Public
    0.62
     area
    0.62
    High
    0.61
    Activations Density 0.225%

    No Known Activations