© 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. 31-GEMMASCOPE-RES-16K
    11. 5692
    Prev
    Next
    INDEX
    Explanations

    references to locations and community dynamics

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

    phrases describing locations within a town or city, particularly using the pattern "of [the] [adjective] part of town."

    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
     ویکی‌پدیا
    -0.38
    änden
    -0.38
    </tfoot>
    -0.37
     הל
    -0.35
     ini
    -0.34
    zysty
    -0.34
     My
    -0.34
     Ald
    -0.33
    ll
    -0.32
    gy
    -0.32
    POSITIVE LOGITS
     town
    2.70
     TOWN
    1.80
    town
    1.72
    Town
    1.62
    TOWN
    1.56
     Town
    1.56
     towns
    1.38
     cidade
    1.13
     city
    1.12
     ciudad
    1.12
    Activations Density 0.148%

    No Known Activations