© 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. 16144
    Prev
    Next
    INDEX
    Explanations

    names of people associated with local businesses or organizations

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

    personal names, particularly first names and surnames of individuals mentioned in biographical or narrative 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
    typeorm
    -0.46
    保有
    -0.43
     Bayard
    -0.42
     Southwestern
    -0.42
     Harlan
    -0.41
     diapers
    -0.40
     DeWitt
    -0.40
     nécessairement
    -0.39
     favorable
    -0.39
     Calhoun
    -0.39
    POSITIVE LOGITS
     rhestr
    0.65
    Whilst
    0.60
     whilst
    0.60
     Whilst
    0.58
     (£
    0.56
     enquiries
    0.55
     Enquiries
    0.53
    Rhestr
    0.53
     MBE
    0.50
     Tutte
    0.50
    Activations Density 0.276%

    No Known Activations