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. 25-GEMMASCOPE-RES-16K
    6. 7916
    Prev
    Next
    INDEX
    Explanations

    numerical data and punctuations in the context of scientific or statistical information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.72
    WriteTagHelper
    -0.71
    ThroughAttribute
    -0.71
    DotNetBar
    -0.67
     utafitiHapana
    -0.62
    BeginContext
    -0.62
    ArrowToggle
    -0.61
     himo
    -0.57
    Getenv
    -0.57
     toArray
    -0.56
    POSITIVE LOGITS
     thanks
    0.61
    thanks
    0.61
     thank
    0.60
    Ta
    0.58
    thank
    0.57
     answer
    0.54
     THANK
    0.53
    Thanks
    0.52
    Tk
    0.51
    help
    0.50
    Activations Density 0.185%

    No Known Activations