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. 0-GEMMASCOPE-RES-16K
    6. 3480
    Prev
    Next
    INDEX
    Explanations

    references to the act of diving or aspects related to depths and exploration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.53
    XmlEnum
    -0.50
     redaktion
    -0.49
    hang
    -0.48
    ts
    -0.47
    τ
    -0.45
    ńczy
    -0.45
    Thickness
    -0.45
     aş
    -0.44
    tt
    -0.44
    POSITIVE LOGITS
     виправивши
    0.93
    BeginContext
    0.88
     NSCoder
    0.78
    évaluateur
    0.76
     otomatig
    0.76
    onViewCreated
    0.74
     defaultstate
    0.74
    makeText
    0.71
    RenderAtEndOf
    0.70
     "");
    
    0.70
    Activations Density 0.134%

    No Known Activations