© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 8198
    Prev
    Next
    INDEX
    Explanations

    connections between characters and their actions/events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Comes after a form of "to be."

    np_acts-logits-general · gemini-2.0-flash

    coming home

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    र्ष
    -0.43
    บาท
    -0.42
     otomatig
    -0.41
    yser
    -0.41
    LER
    -0.40
    Tx
    -0.39
     duros
    -0.39
     Beloved
    -0.39
    áh
    -0.38
    fillment
    -0.38
    POSITIVE LOGITS
    Clik
    0.85
    IVEREF
    0.76
    LayoutStyle
    0.71
    InputBorder
    0.67
     contextLoads
    0.65
     BorderRadius
    0.65
    addCriterion
    0.64
    cestry
    0.63
     виправивши
    0.62
     Phry
    0.62
    Activations Density 0.324%

    No Known Activations