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. 16-GEMMASCOPE-RES-16K
    6. 9154
    Prev
    Next
    INDEX
    Explanations

    references to mathematical formulas, symbols, or notation

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

    "Q" followed by other characters

    np_acts-logits-general · gemini-2.0-flash

    questions and words starting with q

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    脚注の使い方
    -0.80
     itſelf
    -0.78
    BitmapFactory
    -0.73
    بوابة
    -0.73
    таратура
    -0.72
    Personensuche
    -0.72
    — 
    -0.68
    hoeddwyd
    -0.68
    IndentedString
    -0.67
     CommandType
    -0.67
    POSITIVE LOGITS
     Q
    1.06
     q
    1.06
     QU
    0.91
     qs
    0.90
    q
    0.90
    qc
    0.89
    QC
    0.89
    Q
    0.87
     Qu
    0.86
     Quar
    0.83
    Activations Density 0.391%

    No Known Activations