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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 127909
    Prev
    Next
    INDEX
    Explanations

    notations related to statistical estimators and their parameters

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

    effect(iveness) estimators

    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
    ungszeit
    -0.39
     openly
    -0.38
     outright
    -0.37
     ISNI
    -0.37
     certainly
    -0.37
     plunge
    -0.37
     Wohnzimmer
    -0.37
     Lar
    -0.37
    chengladbach
    -0.36
    ätigkeit
    -0.36
    POSITIVE LOGITS
     hiệu
    2.55
    ệu
    1.75
     효
    1.15
     effectiveness
    1.02
    효
    0.98
     effec
    0.96
     efic
    0.93
    効果
    0.93
     Effectiveness
    0.91
    效
    0.90
    Activations Density 0.002%

    No Known Activations