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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3635
    Prev
    Next
    INDEX
    Explanations

    terms related to friction and traction in mechanical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tableFuture
    -0.32
     zaw
    -0.29
    stddef
    -0.29
    /**
    -0.28
    허
    -0.28
     meeting
    -0.28
     volet
    -0.28
    getView
    -0.28
    înd
    -0.27
    ve
    -0.26
    POSITIVE LOGITS
     Grip
    0.75
    Personendaten
    0.73
    Grip
    0.73
     antidesliz
    0.69
     grip
    0.68
    MessageTagHelper
    0.67
    grip
    0.66
     slippage
    0.66
     friction
    0.66
    clusal
    0.63
    Activations Density 0.287%

    No Known Activations