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. 8666
    Prev
    Next
    INDEX
    Explanations

    references and mentions of concepts or items 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
    parker
    -0.69
     guts
    -0.62
     alá
    -0.62
     Kamil
    -0.60
     recevrez
    -0.56
     Wei
    -0.56
     Wal
    -0.56
    STL
    -0.56
     livers
    -0.55
    Ellie
    -0.55
    POSITIVE LOGITS
     Mention
    1.76
     mention
    1.74
     mentions
    1.71
     Mentions
    1.68
     mentioning
    1.65
    Mention
    1.63
    mention
    1.56
     mentioned
    1.55
     Mentioned
    1.46
    mentions
    1.42
    Activations Density 0.047%

    No Known Activations