© 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. 38-GEMMASCOPE-RES-16K
    11. 7305
    Prev
    Next
    INDEX
    Explanations

    questions and phrases related to requests for information or help

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Something
    -0.93
    Something
    -0.93
    something
    -0.90
     SOMETHING
    -0.84
     Wherever
    -0.81
    Wherever
    -0.80
     Whatever
    -0.79
    somewhere
    -0.78
    whatever
    -0.77
    Someone
    -0.75
    POSITIVE LOGITS
     anyway
    0.59
     EconPapers
    0.57
     anty
    0.56
    反正
    0.54
    Geplaatst
    0.52
    دانشنامهٔ
    0.51
     disambiguazione
    0.48
     absolutely
    0.47
     resourceCulture
    0.47
     anyways
    0.46
    Activations Density 0.248%

    No Known Activations