Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 65426
    Prev
    Next
    INDEX
    Explanations

    references to specific organizations, names, or terminologies related to various fields such as energy, history, genetics, and events

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

    Haley, ECM, rhino, Stacey

    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
    uxxxx
    -0.56
    GEBURTSDATUM
    -0.53
    DrawerLayout
    -0.51
    AppRoutingModule
    -0.50
    getDoctrine
    -0.50
     SwiftUI
    -0.49
    ArgumentParser
    -0.49
    complexType
    -0.48
     Unwin
    -0.48
     Petitioners
    -0.48
    POSITIVE LOGITS
     Haley
    0.78
     Rhino
    0.71
    Rhino
    0.68
    Haley
    0.66
     GHG
    0.57
    GHG
    0.53
     rhino
    0.52
     Stacy
    0.51
    Personensuche
    0.49
     Halley
    0.47
    Activations Density 0.029%

    No Known Activations