© 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. 7090
    Prev
    Next
    INDEX
    Explanations

    instances of the word "In" at the beginning of sentences or phrases

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

    "In" followed by a common word

    np_acts-logits-general · gemini-2.0-flash

    the word "In"

    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
     Италијани
    -0.71
     snippetHide
    -0.63
    ValueStyle
    -0.63
    tagHelperRunner
    -0.60
    BibitemShut
    -0.60
    CppMethod
    -0.59
     HasFactory
    -0.59
    nodoc
    -0.59
     ujednoznacz
    -0.58
    Tikang
    -0.58
    POSITIVE LOGITS
    In
    0.56
     In
    0.52
    On
    0.46
    În
    0.45
     On
    0.45
     În
    0.40
     وفي
    0.39
    At
    0.37
     šķ
    0.37
    For
    0.35
    Activations Density 0.319%

    No Known Activations