© 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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10680
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "text" in various contexts

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

    HTML or code snippets containing the word "text"

    np_acts-logits-general · gemini-2.0-flash

    html and javascript code snippets

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Osorio
    -0.55
     useDispatch
    -0.49
    mpion
    -0.45
    oredCriteria
    -0.45
     Kula
    -0.45
     Hau
    -0.44
     Soriano
    -0.43
     Thier
    -0.43
    Hau
    -0.43
    arran
    -0.41
    POSITIVE LOGITS
    text
    2.27
     text
    1.83
    Text
    1.80
     Text
    1.76
    TEXT
    1.52
     TEXT
    1.35
     texte
    1.22
    getText
    1.21
     texts
    1.16
    setText
    1.13
    Activations Density 0.057%

    No Known Activations