Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 122853
    Prev
    Next
    INDEX
    Explanations

    medical terms and conditions related to illness or treatment processes

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

    Technical terminology and specialized vocabulary from scientific, medical, and technical domains appearing in professional or academic contexts.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     ProtoMessage
    -0.49
     Taktlose
    -0.47
    ArrowToggle
    -0.42
     Oblig
    -0.39
    XmlIgnore
    -0.38
    ExtendWith
    -0.37
    Espèce
    -0.36
    exitRule
    -0.36
     AssemblyCulture
    -0.35
    Ӕ
    -0.35
    POSITIVE LOGITS
     ostavi
    0.59
     typelib
    0.56
    ьаж
    0.53
     незавершена
    0.52
     ब्रेकडाउन
    0.52
    LabelTagHelper
    0.52
     Administrativna
    0.49
     ویکی‌پدیای
    0.49
     تكبرها
    0.48
    hysema
    0.47
    Activations Density 0.331%

    No Known Activations