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. 20-GEMMASCOPE-RES-16K
    6. 12684
    Prev
    Next
    INDEX
    Explanations

    the beginning of a document or a significant structure within texts

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

    Immediately after specific punctuation

    np_acts-logits-general · gemini-2.0-flash

    introduction sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mum
    -0.47
     ums
    -0.46
    atche
    -0.46
    CIF
    -0.46
     мол
    -0.46
    tij
    -0.43
    encji
    -0.43
     newBuilder
    -0.43
     />\
    -0.43
    rafo
    -0.42
    POSITIVE LOGITS
    tagHelperRunner
    0.81
    AxisAlignment
    0.73
    出版年
    0.69
    原始内容存档于
    0.69
    følgelig
    0.65
     Efq
    0.63
     nakalista
    0.59
     correctes
    0.58
     Theſe
    0.57
    最快更新
    0.56
    Activations Density 0.048%

    No Known Activations