Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 15-GEMMASCOPE-RES-16K
    6. 2415
    Prev
    Next
    INDEX
    Explanations

    references to sports matches and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -0.82
    PhysRev
    -0.75
     preſent
    -0.72
     ſeveral
    -0.72
     itſelf
    -0.71
     uſed
    -0.71
     ſtate
    -0.70
    ungkinkan
    -0.70
     pleaſure
    -0.70
     myſelf
    -0.69
    POSITIVE LOGITS
     fellow
    0.66
    webElementXpaths
    0.56
     against
    0.55
     rival
    0.54
    lioni
    0.51
    stateMutability
    0.51
     dabei
    0.50
    rawDesc
    0.49
     hapless
    0.48
     face
    0.47
    Activations Density 0.078%

    No Known Activations