© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 9277
    Prev
    Next
    INDEX
    Explanations

    statistical analysis methods related to regression

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

    Statistical and mathematical methods

    np_acts-logits-general · gemini-2.0-flash

    statistical methods and regression analysis

    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
    tvguidetime
    -0.66
     Taktlose
    -0.60
    httphttps
    -0.56
    Datuak
    -0.56
    setVerticalGroup
    -0.54
    RTLR
    -0.53
     للاسماء
    -0.51
    PYX
    -0.50
    igator
    -0.50
    WebVitals
    -0.50
    POSITIVE LOGITS
     technique
    0.82
     techniques
    0.74
     approach
    0.74
     method
    0.71
     theory
    0.69
     methodology
    0.62
     móds
    0.60
     metode
    0.56
     principle
    0.55
     yöntem
    0.54
    Activations Density 1.880%

    No Known Activations