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. 4391
    Prev
    Next
    INDEX
    Explanations

    file formats and their associated functions

    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
    expandindo
    -1.07
    IndentedString
    -1.02
    脚注の使い方
    -0.92
    AndEndTag
    -0.92
     ComVisible
    -0.88
    Geplaatst
    -0.88
    MemoryWarning
    -0.86
    principalTable
    -0.83
    addCriterion
    -0.81
     lenker
    -0.80
    POSITIVE LOGITS
    <h6>
    0.52
    Câu
    0.48
     Tru
    0.45
      
    0.44
    <em>
    0.44
    期刊论文
    0.44
    rog
    0.43
    leistung
    0.43
    <b>
    0.43
    он
    0.43
    Activations Density 0.030%

    No Known Activations