© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 6668
    Prev
    Next
    INDEX
    Explanations

    technical terms related to lubrication and wear resistance 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 @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.57
    canActivate
    -0.42
    NamedQuery
    -0.39
     bassin
    -0.38
    spells
    -0.38
    SPELL
    -0.38
     Shrink
    -0.36
    鎮
    -0.35
     buster
    -0.35
    WebVitals
    -0.35
    POSITIVE LOGITS
     rubbing
    1.62
     scratching
    1.47
     scratch
    1.47
     rubbed
    1.45
     rubs
    1.39
     scraping
    1.38
     friction
    1.34
     scratched
    1.31
     Scratch
    1.29
    scratch
    1.28
    Activations Density 0.726%

    No Known Activations