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. 16340
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and relationships involving derivatives and bounds

    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
     spin
    -0.48
    thumbsup
    -0.47
    aczy
    -0.46
    ύ
    -0.43
    Cran
    -0.42
     spun
    -0.42
    liston
    -0.41
    ronic
    -0.41
     cosmic
    -0.41
     columnIndex
    -0.40
    POSITIVE LOGITS
    исленность
    0.85
    WriteTagHelper
    0.84
     GenerationType
    0.72
    peq
    0.71
     LUMP
    0.71
    tagHelperRunner
    0.71
    หวัด
    0.70
    fjspx
    0.70
     Disqus
    0.70
     oeufs
    0.69
    Activations Density 0.372%

    No Known Activations