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. 717
    Prev
    Next
    INDEX
    Explanations

    products and their associated details or descriptions

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

    Descriptions, details, or specifications of products/articles/solutions

    np_acts-logits-general · gemini-2.0-flash

    content type descriptors

    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
    httphttps
    -0.89
    دانشنامهٔ
    -0.76
     AssemblyCulture
    -0.76
     protoimpl
    -0.71
    ."),
    -0.69
    AddHtmlAttribute
    -0.68
    脚注の使い方
    -0.66
     CreateTagHelper
    -0.65
     nahilalakip
    -0.65
    الإنجليزية
    -0.64
    POSITIVE LOGITS
     number
    0.58
     Details
    0.58
     contd
    0.57
     description
    0.56
    টি
    0.56
     name
    0.55
     details
    0.54
     này
    0.53
     summary
    0.52
     ends
    0.51
    Activations Density 0.492%

    No Known Activations