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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 105393
    Prev
    Next
    INDEX
    Explanations

    terms related to health and physiological measurements, particularly focusing on physical activity and related health issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    pmc
    -0.43
    BindView
    -0.40
     vuoden
    -0.40
    DockStyle
    -0.40
     camicia
    -0.39
    الدراسه
    -0.39
    ➞
    -0.38
    endphp
    -0.38
     fling
    -0.37
    Дереккөздер
    -0.37
    POSITIVE LOGITS
    farin
    0.43
    usitis
    0.42
     Curling
    0.41
    cinogenicity
    0.41
    addEdge
    0.41
    icylic
    0.40
    FTFY
    0.40
     незавершена
    0.39
     revenu
    0.39
     impulso
    0.39
    Activations Density 0.203%

    No Known Activations