© 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. 7180
    Prev
    Next
    INDEX
    Explanations

    mentions of collections or compilations of stories and written works

    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
     kasarigan
    -0.45
    RTSN
    -0.45
    itability
    -0.41
     ویکی‌پدی
    -0.40
    __*/
    -0.40
    JspWriter
    -0.39
    queryInterface
    -0.39
    決して
    -0.39
    ackerel
    -0.38
    pirable
    -0.38
    POSITIVE LOGITS
     instead
    3.92
    Instead
    3.47
     Instead
    3.44
    instead
    3.39
     invece
    2.84
     вместо
    2.64
     istället
    2.41
     zamiast
    2.41
    代わりに
    2.17
     vielmehr
    2.06
    Activations Density 1.209%

    No Known Activations