© 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. 7273
    Prev
    Next
    INDEX
    Explanations

    technical terms and language related to scientific notation and data presentation

    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
    LookAnd
    -0.43
    Искәрмәләр
    -0.40
    SequentialGroup
    -0.40
    الدراسه
    -0.34
    ワイイ
    -0.34
    parsedMessage
    -0.34
     initComponents
    -0.33
    contentLoaded
    -0.33
    bootstrapcdn
    -0.33
    Personensuche
    -0.32
    POSITIVE LOGITS
     writing
    3.50
     write
    3.20
     Writing
    3.08
     wrote
    2.98
     written
    2.94
    writing
    2.94
    Writing
    2.92
     Write
    2.88
     writes
    2.80
    write
    2.75
    Activations Density 3.040%

    No Known Activations