© 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. 39-GEMMASCOPE-RES-16K
    6. 3339
    Prev
    Next
    INDEX
    Explanations

    elements related to blood cell counts and immunological metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرياضيه
    -0.44
    ագրություններ
    -0.42
     الحره
    -0.37
    Autoritní
    -0.37
     Signalez
    -0.36
    setVerticalGroup
    -0.35
    GEBURTSDATUM
    -0.35
     становника
    -0.34
    RTLR
    -0.34
    itag
    -0.32
    POSITIVE LOGITS
     T
    3.00
    T
    2.39
     t
    2.13
    getT
    1.76
     ت
    1.59
     Т
    1.59
    T
    1.54
    t
    1.35
    Т
    1.28
     т
    1.27
    Activations Density 3.691%

    No Known Activations