© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 15336
    Prev
    Next
    INDEX
    Explanations

    terms related to adherence and adhesion in medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sono
    -0.68
     EconPapers
    -0.61
     становника
    -0.61
    tingly
    -0.59
    awtextra
    -0.59
    MigrationBuilder
    -0.58
     Wayback
    -0.57
     XNUMX
    -0.56
    छे
    -0.56
    ГЛА
    -0.56
    POSITIVE LOGITS
    Ad
    0.79
     Ad
    0.78
    ibol
    0.75
    choenen
    0.75
    prod
    0.74
    Einzelnachweise
    0.70
     âgées
    0.70
     économies
    0.69
     religieuses
    0.68
     bär
    0.67
    Activations Density 0.082%

    No Known Activations