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. 18-GEMMASCOPE-RES-16K
    6. 10875
    Prev
    Next
    INDEX
    Explanations

    corporate and company names, particularly in legal and financial contexts

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

    Abbreviations for company names

    np_acts-logits-general · gemini-2.0-flash

    inc. or ltd. company names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Inc
    -0.89
    inc
    -0.89
     Inc
    -0.81
     inc
    -0.76
    IndentedString
    -0.73
    сылкі
    -0.69
     للاسماء
    -0.68
    INC
    -0.65
    setVerticalGroup
    -0.63
    "]);
    
    -0.62
    POSITIVE LOGITS
     ("
    0.63
     dba
    0.61
    .,
    0.59
     headquartered
    0.58
     nieuws
    0.54
     (“
    0.54
     المتحدة
    0.52
    dba
    0.49
     subsidiaries
    0.49
    onyms
    0.48
    Activations Density 0.165%

    No Known Activations