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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 46550
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "ready" in various forms

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

    ready to or for

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     the
    -0.50
    FileStream
    -0.43
     function
    -0.42
    isDeleted
    -0.42
    moduleName
    -0.41
     http
    -0.39
     isNameExpr
    -0.39
     Colleen
    -0.38
    toHexString
    -0.38
    boxShadow
    -0.38
    POSITIVE LOGITS
     Ready
    1.32
     ready
    1.27
    Ready
    1.24
     READY
    1.21
    ready
    1.17
    READY
    1.16
     readiness
    1.05
     siap
    0.99
     Readiness
    0.96
    prepared
    0.94
    Activations Density 0.007%

    No Known Activations