© 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. 23-GEMMASCOPE-RES-16K
    11. 7215
    Prev
    Next
    INDEX
    Explanations

    expressions of physical force and compulsion in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GeoNames
    -0.78
    Geplaatst
    -0.74
     متعلقه
    -0.72
    AfterClass
    -0.72
    roidered
    -0.68
    发表于
    -0.67
    __*/
    -0.64
     wireType
    -0.63
    verwijspagina
    -0.63
    '}>
    -0.63
    POSITIVE LOGITS
     majeure
    1.13
     Maje
    0.86
     majeur
    0.86
     maje
    0.74
    fulness
    0.70
    fully
    0.63
     exerted
    0.61
     constater
    0.60
    bkz
    0.57
    ps
    0.54
    Activations Density 0.090%

    No Known Activations