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

    Neuronpedia

    Jacobian LensNEW
    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. 15689
    Prev
    Next
    INDEX
    Explanations

    mentions of collaborations and team formations

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

    succession or accompaniment

    np_acts-logits-general · gemini-2.0-flash

    joined or followed by

    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
     aasta
    -0.59
    ownika
    -0.47
     tatuaje
    -0.47
    tica
    -0.47
    ControllerAdvice
    -0.45
     vakantie
    -0.45
     sekal
    -0.45
     decorativo
    -0.45
    Reusable
    -0.44
    owników
    -0.42
    POSITIVE LOGITS
     followed
    2.12
    followed
    1.81
     Followed
    1.72
    Followed
    1.62
     accompanied
    1.61
     seguido
    1.57
     diikuti
    1.52
     joined
    1.45
     complemented
    1.43
     flanked
    1.40
    Activations Density 0.633%

    No Known Activations