© 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. 2-GEMMASCOPE-RES-16K
    6. 6882
    Prev
    Next
    INDEX
    Explanations

    references to studies and reports related to social and health issues

    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
    AccessorTable
    -0.87
     surla
    -0.84
    UnitTesting
    -0.75
    expandindo
    -0.74
     comuniques
    -0.74
    QMetaType
    -0.74
    原始内容存档于
    -0.71
    tagHelper
    -0.69
    存于互联网档案馆
    -0.68
    ^*)
    -0.68
    POSITIVE LOGITS
    zło
    0.47
     Desarrollo
    0.44
     tịch
    0.43
    nelse
    0.43
     помочь
    0.41
    ahalli
    0.41
     resmi
    0.40
     secr
    0.40
    ftype
    0.39
    .
    0.39
    Activations Density 0.428%

    No Known Activations