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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53419
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce examples or specify details

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

    listing things with "as" or "including"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HtmlAttribute
    -0.48
     arşivlendi
    -0.42
     незавершена
    -0.40
     authority
    -0.40
     nakalista
    -0.39
     Authority
    -0.39
     azar
    -0.38
     forem
    -0.36
    behörde
    -0.36
    AuthContext
    -0.36
    POSITIVE LOGITS
    Билгалдахарш
    0.88
    INCLUDING
    0.86
     including
    0.82
    awaiter
    0.78
     Including
    0.78
    Including
    0.75
    including
    0.73
     включая
    0.72
    '},
    
    0.70
     INCLUDING
    0.68
    Activations Density 0.241%

    No Known Activations