© 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. 4283
    Prev
    Next
    INDEX
    Explanations

    terms related to measurements and regions in quantitative analysis

    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
     ویکی‌پدی
    -0.56
     ujednoznacz
    -0.47
    المناصب
    -0.45
    ganu
    -0.44
     informée
    -0.41
    новништво
    -0.40
    ValueGenerated
    -0.38
    gehende
    -0.37
    scrollTop
    -0.36
    putExtra
    -0.36
    POSITIVE LOGITS
     lies
    1.93
     sits
    1.71
     resides
    1.67
     lie
    1.59
     reside
    1.46
     sit
    1.42
     resided
    1.30
     Lies
    1.29
     ligger
    1.19
     berada
    1.17
    Activations Density 0.755%

    No Known Activations