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. 24-GEMMASCOPE-RES-16K
    6. 14081
    Prev
    Next
    INDEX
    Explanations

    network addresses, particularly in the format of IP addresses

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

    IP addresses (often 127.0.0.1 or 192.168.x.x)

    np_acts-logits-general · gemini-2.0-flash

    ip addresses

    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
    setVerticalGroup
    -0.59
    っこう
    -0.54
     мәгълү
    -0.53
     IndexPath
    -0.52
    μβρίου
    -0.52
    المشاركات
    -0.52
    lofen
    -0.52
    FieldDescriptor
    -0.50
    essoal
    -0.50
    Tage
    -0.50
    POSITIVE LOGITS
    localhost
    0.68
     Roskov
    0.66
     localhost
    0.58
    homonymie
    0.56
     Seeder
    0.52
     hosting
    0.51
     CreateTagHelper
    0.51
    Datuak
    0.50
    Tembelea
    0.49
    جغرافيا
    0.49
    Activations Density 0.117%

    No Known Activations