© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 102344
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication and interactions, especially in the context of conveying messages and instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     suction
    -0.42
    afficheront
    -0.42
     Grover
    -0.35
    OPSIS
    -0.34
     shel
    -0.34
     Suction
    -0.34
     AG
    -0.33
    cozy
    -0.33
     cast
    -0.32
    uló
    -0.32
    POSITIVE LOGITS
     propOrder
    0.64
    Espèce
    0.60
    InitStruct
    0.56
    تقاوى
    0.56
    Geplaatst
    0.55
    LookAnd
    0.54
    */),
    0.53
     ffilmiau
    0.49
    AnchorTagHelper
    0.49
     desmotivaciones
    0.49
    Activations Density 0.059%

    No Known Activations