Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 8509
    Prev
    Next
    INDEX
    Explanations

    specific terms and phrases from multiple languages

    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
     OMITBAD
    -0.58
    rungsseite
    -0.55
     estekak
    -0.55
    :✨
    -0.53
    tagHelperRunner
    -0.52
    Datuak
    -0.52
    تقاوى
    -0.52
     ddelweddau
    -0.52
     <<<<<<<<<<<<<<
    -0.52
    UrlResolution
    -0.51
    POSITIVE LOGITS
    zbęd
    0.38
    Obfuscated
    0.33
    🇶
    0.32
    CloseOperation
    0.31
     tengah
    0.31
     untersch
    0.31
     JsonConvert
    0.30
     chyba
    0.30
     bestaan
    0.29
     uska
    0.29
    Activations Density 0.075%

    No Known Activations