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. 8-GEMMASCOPE-RES-16K
    6. 14927
    Prev
    Next
    INDEX
    Explanations

    terms related to automotive parts and maintenance, particularly focusing on installation and replacement of components

    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
     createState
    -0.68
     surla
    -0.67
     whither
    -0.64
    wherein
    -0.63
     فريبيس
    -0.63
     استنادى
    -0.62
     Grüsse
    -0.61
     whence
    -0.61
     Diretto
    -0.61
    Filmografie
    -0.60
    POSITIVE LOGITS
     replacements
    0.54
    InputTagHelper
    0.51
     replacement
    0.51
    twimg
    0.48
     JButton
    0.47
     strada
    0.47
     installa
    0.47
    replace
    0.46
     install
    0.46
    wpi
    0.46
    Activations Density 0.134%

    No Known Activations