© 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. 20-GEMMASCOPE-RES-16K
    6. 14725
    Prev
    Next
    INDEX
    Explanations

    specific references to tax-related topics and changes in tax legislation

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

    Follows verbs indicating investigation or implementation

    np_acts-logits-general · gemini-2.0-flash

    learn, look, seen, flesh

    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
     فريبيس
    -0.56
     onPostExecute
    -0.54
    بوابة
    -0.50
     Taktlose
    -0.49
     zawsze
    -0.49
     مشين
    -0.47
    Xna
    -0.47
    ClientRect
    -0.46
    fitrión
    -0.46
     RoutedEventArgs
    -0.45
    POSITIVE LOGITS
     hyped
    0.41
     excited
    0.38
     nerfed
    0.38
     leaked
    0.37
     adapted
    0.37
     affected
    0.36
     implemented
    0.36
     adapt
    0.35
     disseminated
    0.35
    endum
    0.35
    Activations Density 0.575%

    No Known Activations