© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 4349
    Prev
    Next
    INDEX
    Explanations

    references to individuals involved in medical or legal settings

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

    professional roles and titles of individuals in formal contexts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Meksiku
    -0.60
     Paying
    -0.55
    Paying
    -0.55
     poffible
    -0.53
    awtextra
    -0.52
     membayar
    -0.51
     appointing
    -0.50
     poveznice
    -0.50
     Exacts
    -0.49
    DockStyle
    -0.49
    POSITIVE LOGITS
     working
    0.65
    working
    0.57
     job
    0.52
     handling
    0.50
     handle
    0.50
     report
    0.50
     expertise
    0.50
     work
    0.49
    Working
    0.48
     bekerja
    0.48
    Activations Density 0.781%

    No Known Activations