© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 17474
    Prev
    Next
    INDEX
    Explanations

    references to mechanical components, specifically rods and rod structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    rod

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     فريبيس
    -0.58
    Alli
    -0.50
     Quer
    -0.49
    WESTERN
    -0.48
    :
    
    -0.48
     Keynes
    -0.48
    Heritage
    -0.48
     Cele
    -0.48
     Laurence
    -0.47
     Fairfax
    -0.47
    POSITIVE LOGITS
     rod
    1.95
     rods
    1.80
     Rods
    1.57
    rod
    1.43
    rods
    1.30
    Rod
    1.12
    ROD
    1.08
     Rod
    1.08
     ROD
    1.01
    ロッド
    0.94
    Activations Density 0.004%

    No Known Activations