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. 14865
    Prev
    Next
    INDEX
    Explanations

    discussions on the impact of drugs, particularly related to relief and addiction treatment

    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
    setViewportView
    -0.43
    ModelSerializer
    -0.41
     arşivlendi
    -0.36
    AnchorTagHelper
    -0.35
     }{@
    -0.35
    minecraftforge
    -0.35
     تكبرها
    -0.35
    показания
    -0.35
     MainAxisSize
    -0.34
    PointerException
    -0.32
    POSITIVE LOGITS
     thousands
    3.39
     hundreds
    3.06
    thousands
    3.03
     Thousands
    2.91
     millions
    2.88
    Thousands
    2.88
    hundreds
    2.73
     Hundreds
    2.69
    Hundreds
    2.67
     tens
    2.50
    Activations Density 1.073%

    No Known Activations