© 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
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11387
    Prev
    Next
    INDEX
    Explanations

    concepts related to cellular energy production and oxygen metabolism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     يتيمه
    -0.77
     للاسماء
    -0.70
    ValueStyle
    -0.69
     Nasal
    -0.65
    Datuak
    -0.63
     المعيارى
    -0.61
    iosync
    -0.61
     snippetHide
    -0.61
    oretical
    -0.60
     NSCoder
    -0.60
    POSITIVE LOGITS
     médicale
    0.37
     énergé
    0.36
     médica
    0.33
     nutrición
    0.32
     mecánico
    0.32
     facultad
    0.31
     âgées
    0.31
     formación
    0.30
     constitución
    0.29
     eléctrico
    0.29
    Activations Density 0.241%

    No Known Activations