© 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
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 13907
    Prev
    Next
    INDEX
    Explanations

    specific terms or phrases related to literature or storytelling

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

    Following the token "ने"

    np_acts-logits-general · gemini-2.0-flash

    नेहरू

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.70
    putable
    -0.57
    Jeografia
    -0.56
     تضيفلها
    -0.56
    ashqai
    -0.55
     zuſammen
    -0.54
     dé
    -0.53
    tiefel
    -0.53
     CreateTagHelper
    -0.52
    MethodManager
    -0.52
    POSITIVE LOGITS
     henvisninger
    0.47
    曖昧さ回避
    0.46
     EconPapers
    0.41
    awtextra
    0.40
     pály
    0.39
     ویکی‌پدیای
    0.39
     testigo
    0.38
     illet
    0.37
     politiet
    0.37
     egens
    0.36
    Activations Density 0.004%

    No Known Activations