© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 121405
    Prev
    Next
    INDEX
    Explanations

    terms related to legal definitions and terminology

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

    words starting with "Def"

    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
     kasarigan
    -0.73
    UserScript
    -0.72
    yarnpkg
    -0.72
     Италијани
    -0.70
     betweenstory
    -0.66
    قایناقلار
    -0.65
    Jeografia
    -0.65
     Waterhouse
    -0.63
     Rooms
    -0.61
    Rooms
    -0.59
    POSITIVE LOGITS
     Def
    1.71
    Def
    1.61
    def
    1.38
     DEF
    1.32
     def
    1.29
    DEF
    1.19
     déf
    1.07
     deflection
    0.94
     deflation
    0.88
     deff
    0.87
    Activations Density 0.046%

    No Known Activations