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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 18-GEMMASCOPE-RES-16K
    6. 1110
    Prev
    Next
    INDEX
    Explanations

    business or event-related information, particularly details about conferences or festivals

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

    Information or contact details (URLs, phone numbers)

    np_acts-logits-general · gemini-2.0-flash

    contact www information

    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
    tvguidetime
    -0.77
    
    -0.75
    OGND
    -0.72
    KommentareTeilen
    -0.71
    فایل‌لار
    -0.64
    MENAFN
    -0.63
    
    -0.61
     AllMovie
    -0.60
    pegno
    -0.59
    /*:
    -0.59
    POSITIVE LOGITS
    Visit
    1.02
     Visit
    1.00
    visit
    0.98
     contact
    0.98
     visit
    0.95
    www
    0.94
     www
    0.93
    Contact
    0.92
     Contact
    0.92
    Info
    0.85
    Activations Density 0.090%

    No Known Activations