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. 24-GEMMASCOPE-RES-16K
    6. 14137
    Prev
    Next
    INDEX
    Explanations

    references to legal dates and temporal markers in a document

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

    Dates (day, month, year)

    np_acts-logits-general · gemini-2.0-flash

    dates and filings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.67
     sumpay
    -0.60
    PhysRevD
    -0.59
    itorio
    -0.57
    ilíbrio
    -0.55
     nakalista
    -0.55
    ")));
    
    -0.54
    findpost
    -0.53
    XmlAccessType
    -0.52
     ostavi
    -0.51
    POSITIVE LOGITS
    fjspx
    0.57
    scrapy
    0.52
     مرئيه
    0.49
    SizeMode
    0.47
     salaire
    0.44
     alpina
    0.44
    AutoresizingMask
    0.44
     Partagez
    0.43
    +#+#
    0.43
    Cap
    0.43
    Activations Density 0.137%

    No Known Activations