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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1741
    Prev
    Next
    INDEX
    Explanations

    comments and annotations in code

    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
     fubject
    -0.63
     clearColor
    -0.62
     ſeveral
    -0.61
     itſelf
    -0.59
     occafion
    -0.58
     poffe
    -0.57
     houſe
    -0.54
     purpoſe
    -0.54
     Theſe
    -0.52
     occaf
    -0.52
    POSITIVE LOGITS
     check
    0.88
     then
    0.72
     Check
    0.70
     Then
    0.69
     prepare
    0.66
    AndUpdate
    0.65
    check
    0.65
     kemudian
    0.60
     الحره
    0.58
     get
    0.58
    Activations Density 0.088%

    No Known Activations