© 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. 1298
    Prev
    Next
    INDEX
    Explanations

    terms related to varying levels of intensity or severity, particularly in a medical or evaluative context

    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
     GoFundMe
    -0.61
    IsInitialized
    -0.57
    ImageContext
    -0.56
    НИМА
    -0.56
     '../../
    -0.56
    FundMe
    -0.56
     #%
    -0.55
     immédi
    -0.55
    juris
    -0.55
     jPanel
    -0.54
    POSITIVE LOGITS
     premises
    0.80
     Administrativna
    0.67
    Aiheesta
    0.67
    homonymie
    0.66
     moderate
    0.66
    upsi
    0.64
    matchCondition
    0.64
    paired
    0.63
     premise
    0.63
     kasarigan
    0.63
    Activations Density 0.139%

    No Known Activations