© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7232
    Prev
    Next
    INDEX
    Explanations

    phrases indicating preparedness or willingness

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

    "ready" or "readiness"

    np_acts-logits-general · gemini-2.0-flash

    ready to, ready 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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    toHexString
    -0.44
     the
    -0.43
    filterBy
    -0.35
     Colleen
    -0.33
     which
    -0.32
     مق
    -0.32
     http
    -0.32
    ↵↵
    -0.31
     function
    -0.30
     doméstico
    -0.30
    POSITIVE LOGITS
     ready
    1.45
     Ready
    1.45
    Ready
    1.37
     READY
    1.33
    ready
    1.30
     readiness
    1.26
    READY
    1.24
     Readiness
    1.13
     siap
    1.13
     готов
    1.03
    Activations Density 0.054%

    No Known Activations