© 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. 20-GEMMASCOPE-RES-131K
    11. 105806
    Prev
    Next
    INDEX
    Explanations

    phrases and structures related to technical specifications and product features

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

    foreign words or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pinulongan
    -0.60
     ujednoznacz
    -0.58
    期刊论文
    -0.56
    IUrlHelper
    -0.49
    PerformLayout
    -0.48
     deci
    -0.46
     Normdatei
    -0.46
    TimerTask
    -0.46
    얻
    -0.45
     Ue
    -0.45
    POSITIVE LOGITS
     amitié
    0.54
     mármol
    0.47
     gouden
    0.44
     habilidad
    0.44
     mecán
    0.44
     profondità
    0.43
     adaptación
    0.43
     gjerne
    0.43
     conflits
    0.42
     chiusura
    0.42
    Activations Density 0.056%

    No Known Activations