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. 7411
    Prev
    Next
    INDEX
    Explanations

    phrases related to underlying mechanisms and factors influencing various processes

    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
    sizePolicy
    -0.60
    們
    -0.57
    存于互联网档案馆
    -0.56
     merve
    -0.55
    Hozzáférés
    -0.54
    They
    -0.48
    们
    -0.48
     Pristupljeno
    -0.46
    ándote
    -0.45
     circonstances
    -0.45
    POSITIVE LOGITS
     certain
    0.83
     both
    0.80
     these
    0.79
     poszczegól
    0.75
     such
    0.73
     various
    0.71
     zowel
    0.65
     bestimmte
    0.63
     determinados
    0.62
     bepaalde
    0.61
    Activations Density 1.937%

    No Known Activations