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. 5231
    Prev
    Next
    INDEX
    Explanations

    references to "this" and its variations in texts

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

    "This" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    This was/is/led to

    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
     élu
    -0.55
    réhen
    -0.54
    diano
    -0.51
    slidesPer
    -0.51
    juta
    -0.51
     bénéfice
    -0.51
    yelitis
    -0.50
    providedIn
    -0.49
     себя
    -0.49
     megfelelő
    -0.49
    POSITIVE LOGITS
     '\\;'
    0.75
     مرئيه
    0.71
     nahilalakip
    0.66
     betweenstory
    0.64
     дописавши
    0.61
    ThroughAttribute
    0.59
    InitVars
    0.58
     NSCoder
    0.57
     cherchés
    0.57
     otomatig
    0.57
    Activations Density 0.212%

    No Known Activations