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

    Neuronpedia

    APICircuit 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. 16-GEMMASCOPE-RES-16K
    6. 12312
    Prev
    Next
    INDEX
    Explanations

    word patterns or sequences that repeat in various forms

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

    Unicode characters or currency symbols

    np_acts-logits-general · gemini-2.0-flash

    programming language identifiers

    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
     TextAppearance
    -0.81
     Meksiku
    -0.79
    AutoModerator
    -0.77
    labus
    -0.77
    енча
    -0.75
     otomatig
    -0.75
     betweenstory
    -0.73
    InjectAttribute
    -0.72
    oredCriteria
    -0.72
     PyLong
    -0.72
    POSITIVE LOGITS
    MethodManager
    0.60
    ‚¬
    0.60
    存于互联网档案馆
    0.56
    ionView
    0.55
    уза
    0.51
     onCreateView
    0.51
    ្
    0.49
     holding
    0.49
    cshtml
    0.49
     محفوظة
    0.48
    Activations Density 0.098%

    No Known Activations