© 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. 25-GEMMASCOPE-RES-16K
    11. 4780
    Prev
    Next
    INDEX
    Explanations

    references to graphical elements related to system drawing and size properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defStyle
    -0.70
     tartalomajánló
    -0.66
    parsedMessage
    -0.61
    SourceChecksum
    -0.60
    errHandler
    -0.60
     ostavi
    -0.55
     سكانية
    -0.53
    ftagPool
    -0.52
    __*/
    -0.52
    oglio
    -0.51
    POSITIVE LOGITS
    awtextra
    0.63
     المعيارى
    0.55
    enumi
    0.51
    蛮
    0.47
     leçon
    0.47
     CanadaChoose
    0.46
     CGSize
    0.44
    iets
    0.43
     scolas
    0.43
    essai
    0.43
    Activations Density 0.107%

    No Known Activations