© 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. 32779
    Prev
    Next
    INDEX
    Explanations

    concepts related to achieving goals and progress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     IBOutlet
    -0.64
    хьтан
    -0.59
    tanleria
    -0.57
    CppMethod
    -0.56
    posedge
    -0.54
     MenuView
    -0.52
    يكب
    -0.51
    spyOn
    -0.50
    новништво
    -0.50
    Microkernel
    -0.49
    POSITIVE LOGITS
     achieving
    0.58
     achieve
    0.56
     goals
    0.56
     mencapai
    0.52
     goal
    0.51
     alcanzar
    0.49
     atteindre
    0.49
     attaining
    0.48
     desired
    0.48
     erreichen
    0.47
    Activations Density 0.023%

    No Known Activations