© 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. 8909
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and their reactions

    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
    WebServlet
    -0.44
    ISODE
    -0.43
    TestingModule
    -0.41
     BoxDecoration
    -0.39
     MainAxisSize
    -0.38
    Portály
    -0.37
     समीक्षक
    -0.37
    허
    -0.35
    CodeAttribute
    -0.35
     ComVisible
    -0.35
    POSITIVE LOGITS
     upward
    2.55
     upwards
    2.22
     Up
    1.98
     ascending
    1.90
     ascend
    1.86
     UP
    1.85
     ascent
    1.85
     ascended
    1.78
    Up
    1.77
     вверх
    1.72
    Activations Density 1.445%

    No Known Activations