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. 8-GEMMASCOPE-RES-16K
    6. 5895
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their frequencies in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     blooming
    -0.62
     tandis
    -0.57
     charging
    -0.57
     forgiven
    -0.56
     själ
    -0.56
     spelling
    -0.56
     tangential
    -0.56
     unfolding
    -0.55
     whereas
    -0.55
     typing
    -0.55
    POSITIVE LOGITS
     will
    1.20
     has
    1.14
     could
    1.09
     had
    1.06
     would
    1.05
     was
    1.05
     have
    1.04
     is
    1.03
     must
    0.98
     might
    0.94
    Activations Density 0.356%

    No Known Activations