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

    Neuronpedia

    APICircuit 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. 5-GEMMASCOPE-RES-16K
    6. 1489
    Prev
    Next
    INDEX
    Explanations

    technical terms related to domain name system configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     endwhile
    -0.71
    endpush
    -0.67
    AccessorTable
    -0.66
    tableFuture
    -0.64
     createSlice
    -0.63
    nonatomic
    -0.61
    脚注の使い方
    -0.60
    +#+#
    -0.60
    UnsafeEnabled
    -0.60
     initComponents
    -0.59
    POSITIVE LOGITS
     DNS
    0.91
    dns
    0.78
    DNS
    0.78
     dns
    0.78
    Dns
    0.73
     IPv
    0.72
    dflare
    0.68
    Ipv
    0.65
     domain
    0.64
    IPv
    0.62
    Activations Density 0.413%

    No Known Activations