© 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. 10-GEMMASCOPE-RES-16K
    11. 5123
    Prev
    Next
    INDEX
    Explanations

    correlation between variables and their statistical analysis in research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.45
     Johansen
    -0.43
    obal
    -0.42
     Winaray
    -0.41
    telo
    -0.40
    “
    -0.40
    örper
    -0.39
    ”
    -0.39
    жества
    -0.39
     Proceeds
    -0.39
    POSITIVE LOGITS
    ########.
    0.81
     propOrder
    0.78
    Personendaten
    0.75
    PreExecute
    0.67
     Roskov
    0.66
     surla
    0.65
    fillType
    0.65
    bibfield
    0.63
     kasarigan
    0.63
     isInitialized
    0.62
    Activations Density 0.761%

    No Known Activations