© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 9920
    Prev
    Next
    INDEX
    Explanations

    references to specific types of food or dining experiences

    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
    webElementXpaths
    -0.64
     الحره
    -0.54
    setVerticalGroup
    -0.52
     ✭✭
    -0.44
    ioutil
    -0.43
    ที่ยว
    -0.41
     كومونز
    -0.41
     toek
    -0.40
    ----</
    -0.40
     coats
    -0.40
    POSITIVE LOGITS
     Alig
    0.43
     IGP
    0.43
    acebook
    0.42
    variation
    0.40
     AssemblyVersion
    0.40
     refine
    0.39
     BIO
    0.39
    contentLoaded
    0.38
     Spec
    0.38
    ecological
    0.38
    Activations Density 0.154%

    No Known Activations