© 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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105776
    Prev
    Next
    INDEX
    Explanations

    measurements and units related to quantities

    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
    原始内容存档于
    -0.43
    IsMutable
    -0.41
     kokona
    -0.41
     řízení
    -0.39
    Telefax
    -0.38
     Betrieb
    -0.38
    IDAE
    -0.38
     Beck
    -0.37
     gehö
    -0.37
     relations
    -0.36
    POSITIVE LOGITS
    DockStyle
    0.79
    
    0.64
    RectangleBorder
    0.53
     oprot
    0.50
    AddTagHelper
    0.49
    ChildScrollView
    0.49
     UIKit
    0.44
    %");
    0.43
    Noct
    0.42
    stateProvider
    0.42
    Activations Density 0.038%

    No Known Activations