© 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-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 9839
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical and biological administration methods and procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .'</
    -0.64
     AspNetCore
    -0.64
     esboço
    -0.64
    NOPQRST
    -0.63
    avyzd
    -0.60
     acquittal
    -0.60
    heça
    -0.59
    RectangleBorder
    -0.58
    endimiento
    -0.58
    pology
    -0.57
    POSITIVE LOGITS
     doses
    0.61
    出版年
    0.58
     dosing
    0.54
    basicConfig
    0.53
     administered
    0.53
     dose
    0.53
    Dose
    0.52
    FormTagHelper
    0.51
    Alone
    0.51
    inject
    0.50
    Activations Density 1.760%

    No Known Activations