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-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1257
    Prev
    Next
    INDEX
    Explanations

    terms related to pathogens and their mechanisms of infection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intégr
    -0.59
    phazard
    -0.53
    AnimationsModule
    -0.52
    الحياه
    -0.50
    SetOutput
    -0.49
     learning
    -0.48
    ciful
    -0.48
    QtCore
    -0.47
    Learning
    -0.47
    learning
    -0.47
    POSITIVE LOGITS
     samples
    0.83
     Samples
    0.75
     sampled
    0.71
    samples
    0.68
    Samples
    0.64
     muestras
    0.63
     analysed
    0.61
     فہرست
    0.60
     SAMPLES
    0.60
     sample
    0.58
    Activations Density 1.899%

    No Known Activations