© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 10792
    Prev
    Next
    INDEX
    Explanations

    references to caregiving and related themes

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

    Follows "the" or a plural possessive

    np_acts-logits-general · gemini-2.0-flash

    the [noun] / assessed via

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.84
     للاسماء
    -0.80
    richTextPanel
    -0.77
    contentLoaded
    -0.74
     désolés
    -0.69
    yntaxException
    -0.65
    OGND
    -0.65
    webElement
    -0.65
     zelve
    -0.64
    ſelf
    -0.63
    POSITIVE LOGITS
     sua
    0.35
    たら
    0.33
     rive
    0.33
     their
    0.32
    ver
    0.31
     seu
    0.30
     occasion
    0.30
     his
    0.30
    ART
    0.30
    tima
    0.29
    Activations Density 0.577%

    No Known Activations