© 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. 7092
    Prev
    Next
    INDEX
    Explanations

    elements related to inquiries and reports regarding personal experiences or testimonies

    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
    verwijspagina
    -0.54
    ✭✭
    -0.47
    くなりました
    -0.44
     okuyayım
    -0.44
    Foi
    -0.42
     wurde
    -0.41
     fue
    -0.41
    になりました
    -0.40
    CodedInputStream
    -0.40
    tvguidetime
    -0.40
    POSITIVE LOGITS
     had
    2.55
    Had
    2.02
     Had
    1.83
     había
    1.80
    had
    1.77
     habían
    1.77
     hadden
    1.61
     hadn
    1.60
     hadde
    1.56
     havia
    1.54
    Activations Density 1.074%

    No Known Activations