© 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. 20-GEMMASCOPE-RES-131K
    11. 79006
    Prev
    Next
    INDEX
    Explanations

    instances of the word "new."

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

    new followed by specific noun

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     voeten
    -0.47
    someone
    -0.44
     someone
    -0.43
    hydrogenase
    -0.43
    igkeit
    -0.42
    ech
    -0.41
    setP
    -0.41
    lastonbury
    -0.40
    ตาย
    -0.40
     alguém
    -0.40
    POSITIVE LOGITS
     Roskov
    0.57
     Administrativna
    0.57
     kaarangay
    0.57
    󠁮
    0.54
    UnusedPrivate
    0.51
    :✨
    0.51
    ⤹
    0.48
     new
    0.46
    󠁣
    0.46
    SharedCtor
    0.45
    Activations Density 0.015%

    No Known Activations