© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 4795
    Prev
    Next
    INDEX
    Explanations

    references to public transportation and related services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iſter
    -0.66
     myſelf
    -0.64
     Monfieur
    -0.63
     juſ
    -0.60
     ſou
    -0.60
     viſ
    -0.59
    ſelves
    -0.58
    檚
    -0.57
     Jefus
    -0.57
    ſelf
    -0.57
    POSITIVE LOGITS
    es
    1.11
    ses
    1.01
    ES
    0.79
    ess
    0.69
    sed
    0.65
    hes
    0.64
    ness
    0.62
    sing
    0.56
    esa
    0.52
    nes
    0.51
    Activations Density 0.960%

    No Known Activations