© 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. 21-GEMMASCOPE-RES-16K
    11. 16087
    Prev
    Next
    INDEX
    Explanations

    specific references to research methodologies and statistical analysis in scientific literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.70
    complexContent
    -0.62
    Filmografie
    -0.61
     OMITBAD
    -0.60
     contextLoads
    -0.59
    awtextra
    -0.57
    istoitu
    -0.56
    ituary
    -0.56
     дописавши
    -0.55
    writeFieldEnd
    -0.55
    POSITIVE LOGITS
    }{*}{
    0.72
    }{*}{}
    0.58
    glGen
    0.56
     ?>/
    0.55
    </strong>
    0.51
    سطس
    0.50
    BeginContext
    0.49
    ContextCompat
    0.49
    ```
    0.48
    cyklopedia
    0.48
    Activations Density 0.104%

    No Known Activations