© 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. 18-GEMMASCOPE-RES-16K
    11. 7064
    Prev
    Next
    INDEX
    Explanations

    activities and themes related to artistic expression and recreational events

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

    after specific sport/activity terms

    np_acts-logits-general · gemini-2.0-flash

    activities and associated items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ParallelGroup
    -0.49
    IActionResult
    -0.48
    ality
    -0.47
    kháu
    -0.46
    Datuak
    -0.46
    mapStateToProps
    -0.45
    leftarrow
    -0.45
     states
    -0.44
    matchCondition
    -0.43
    IBarButtonItem
    -0.43
    POSITIVE LOGITS
     ImportError
    0.67
     sessions
    0.67
     lessons
    0.63
    writeField
    0.61
     JAXBElement
    0.60
     enthusiasts
    0.60
    atorics
    0.60
    ništ
    0.58
     erfre
    0.58
    ättä
    0.57
    Activations Density 0.274%

    No Known Activations