© 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. 15-GEMMASCOPE-RES-16K
    6. 4793
    Prev
    Next
    INDEX
    Explanations

    technical terms related to machinery and manufacturing processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     समीक्षक
    -1.01
    BagConstraints
    -0.71
    исленность
    -0.69
    MessageTagHelper
    -0.65
    AccessFile
    -0.65
     समीक्षाओं
    -0.62
    AnchorStyles
    -0.59
    KEYCODE
    -0.59
    ModelState
    -0.58
     Pristupljeno
    -0.58
    POSITIVE LOGITS
     ویکی‌پدیا
    0.54
     snippetHide
    0.53
     esternos
    0.53
    XmlAccessorType
    0.48
    ExtendWith
    0.47
    XtraGrid
    0.46
     DPRD
    0.46
     Sélectionnez
    0.45
     zoll
    0.45
     aidant
    0.43
    Activations Density 9.056%

    No Known Activations