© 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. 5-GEMMASCOPE-RES-16K
    11. 9438
    Prev
    Next
    INDEX
    Explanations

    expressions related to legal disputes and concerns about governmental or institutional actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Devlin
    -0.57
     yourselves
    -0.56
     tử
    -0.54
     pleaſure
    -0.54
    atoires
    -0.54
     defire
    -0.53
    curité
    -0.53
     للاسماء
    -0.53
     Ush
    -0.52
    لينكات
    -0.51
    POSITIVE LOGITS
    LookAnd
    0.58
     externi
    0.53
     ivelany
    0.51
    Jereo
    0.50
     recentes
    0.48
    mpä
    0.48
    verifyException
    0.47
     cristianos
    0.47
     assolu
    0.47
     sementara
    0.47
    Activations Density 0.424%

    No Known Activations