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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 39285
    Prev
    Next
    INDEX
    Explanations

    gerunds and verbs in various forms indicating actions or processes

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

    verbs followed by objects or prepositions

    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
     arşivlendi
    -0.77
    RotationOrder
    -0.68
     noqa
    -0.67
    AndEndTag
    -0.66
     تضيفلها
    -0.62
     kaarangay
    -0.60
    ResumeLayout
    -0.60
    MLLoader
    -0.59
    Personensuche
    -0.58
    basicConfig
    -0.57
    POSITIVE LOGITS
    Slf
    0.33
    volmente
    0.32
     several
    0.32
    お気軽
    0.32
    Several
    0.32
    stopp
    0.32
    wäh
    0.32
     Several
    0.31
     obtaining
    0.31
     consigo
    0.31
    Activations Density 0.027%

    No Known Activations