© 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. 4-GEMMASCOPE-RES-16K
    11. 10702
    Prev
    Next
    INDEX
    Explanations

    words related to conversion and transformation of quantities or values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DoubleQuotes
    -0.65
    rungsseite
    -0.60
    WritableDatabase
    -0.60
    arXiv
    -0.59
    !*\
    -0.59
     дописавши
    -0.56
    AnchorTagHelper
    -0.55
    ProgressHUD
    -0.55
     &___
    -0.55
    newArrayList
    -0.54
    POSITIVE LOGITS
     '{@
    0.57
    原本
    0.52
    اديم
    0.52
    MessageTagHelper
    0.51
     conver
    0.47
     BytesLike
    0.46
     LIL
    0.46
     trans
    0.45
    __'
    0.44
     Censo
    0.44
    Activations Density 0.786%

    No Known Activations