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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 127701
    Prev
    Next
    INDEX
    Explanations

    the word "are" and its variations

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

    there are many

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     AssemblyCulture
    -0.50
     arşivlendi
    -0.48
     StatelessWidget
    -0.48
    Kaynakça
    -0.46
    InsertCommand
    -0.46
    发表于
    -0.46
     Kontexten
    -0.46
     nonUne
    -0.45
    SharedCtor
    -0.45
     Мексичка
    -0.44
    POSITIVE LOGITS
     total
    0.51
    éron
    0.46
     hierarch
    0.45
     consists
    0.41
     numbered
    0.40
    共有
    0.40
     largest
    0.40
    EROS
    0.40
     consist
    0.39
    不下
    0.39
    Activations Density 0.026%

    No Known Activations