© 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. 105656
    Prev
    Next
    INDEX
    Explanations

    references to dialog boxes and their configuration in a software context

    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
     buffet
    -0.37
     beads
    -0.34
     Überg
    -0.34
    XmlSchema
    -0.33
     espanhol
    -0.33
    いらっしゃ
    -0.32
     garantire
    -0.32
     chất
    -0.32
     bro
    -0.32
     immunity
    -0.32
    POSITIVE LOGITS
     GenerationType
    0.62
    DispatchToProps
    0.54
    IUrlHelper
    0.53
    HideFlags
    0.53
    RefNanny
    0.48
    AutoScaleMode
    0.47
    DIPSETTING
    0.46
    GraphicsUnit
    0.46
    serviceWorker
    0.45
     ProtoMessage
    0.44
    Activations Density 0.011%

    No Known Activations