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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16372
    Prev
    Next
    INDEX
    Explanations

    references to legal entities and locations

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

    Follows "of" or "in" (location context)

    np_acts-logits-general · gemini-2.0-flash

    cities in United States

    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
    RenderAtEndOf
    -0.62
     informée
    -0.60
    soka
    -0.56
    uyện
    -0.51
    ZZLE
    -0.49
    횟
    -0.49
    setCharacter
    -0.49
    Jeografia
    -0.48
     GPS
    -0.48
     Dulles
    -0.47
    POSITIVE LOGITS
     تضيفلها
    0.82
    ArgsConstructor
    0.61
     Pass
    0.54
    
    0.54
     Detroit
    0.53
     iprot
    0.52
     للاسماء
    0.51
    WAUKEE
    0.51
    transQ
    0.50
    (@"%@",
    0.49
    Activations Density 0.197%

    No Known Activations