© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 14112
    Prev
    Next
    INDEX
    Explanations

    terms related to experimental and clinical study designs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Past tense verbs related to studies or experiments

    np_acts-logits-general · gemini-2.0-flash

    study was conducted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     âgées
    -0.60
     disposição
    -0.58
    rapeau
    -0.55
    Separated
    -0.54
    Used
    -0.52
     USED
    -0.51
     torner
    -0.51
     Used
    -0.49
     sẵn
    -0.49
     Employed
    -0.49
    POSITIVE LOGITS
     ended
    0.81
     conducted
    0.78
     berlangsung
    0.73
     involving
    0.71
     undertaken
    0.70
     initiated
    0.68
     begun
    0.66
     underway
    0.65
     dimulai
    0.65
     structured
    0.64
    Activations Density 0.718%

    No Known Activations