© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 114650
    Prev
    Next
    INDEX
    Explanations

    mentions of the Energy Star label and related energy efficiency terms

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

    Star and groovy

    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
    Wahl
    -0.39
     dieß
    -0.38
    AnimationFrame
    -0.38
     nothwendig
    -0.36
     fVar
    -0.36
    IVEREF
    -0.35
    Bayer
    -0.34
     ſind
    -0.34
    Packets
    -0.34
    umph
    -0.33
    POSITIVE LOGITS
     ddelweddau
    0.76
    terraform
    0.67
    lccn
    0.65
    groovy
    0.63
     EconPapers
    0.63
     WorldCat
    0.62
     Americana
    0.61
     nahilalakip
    0.60
    JvmStatic
    0.57
    llac
    0.57
    Activations Density 0.008%

    No Known Activations