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 - 16k
    5. 39-GEMMASCOPE-RES-16K
    6. 2912
    Prev
    Next
    INDEX
    Explanations

    terms related to the detection of particles in scientific experiments

    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
     automatique
    -0.32
     RADIATION
    -0.32
    Beck
    -0.32
    JAKARTA
    -0.31
    BECK
    -0.30
     cedera
    -0.30
    retum
    -0.30
    beck
    -0.30
    setFocus
    -0.30
     recensement
    -0.30
    POSITIVE LOGITS
     neutr
    0.71
     Neu
    0.67
     neutrino
    0.66
    neu
    0.62
     Flavor
    0.61
    Neu
    0.59
    Flavor
    0.58
     виправивши
    0.57
    GEBURTSDATUM
    0.56
     flavor
    0.55
    Activations Density 1.264%

    No Known Activations