© 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. 3911
    Prev
    Next
    INDEX
    Explanations

    references to the left side or left directions in various contexts

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

    left panel

    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
    出版年
    -0.65
    pulseira
    -0.62
    SharedDtor
    -0.60
    NameInMap
    -0.59
     numberWith
    -0.58
    addCriterion
    -0.57
     CGSize
    -0.57
    Rptr
    -0.57
     StringTokenizer
    -0.53
    AddTagHelper
    -0.52
    POSITIVE LOGITS
    Left
    1.05
     Left
    1.02
     left
    0.98
    left
    0.98
    setLeft
    0.87
     LEFT
    0.85
     izquierdo
    0.83
    LEFT
    0.82
     esquerda
    0.80
    getLeft
    0.77
    Activations Density 0.039%

    No Known Activations