© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 13519
    Prev
    Next
    INDEX
    Explanations

    conjunctions and qualifiers that indicate uncertainty or contrasting information

    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
     either
    -0.85
     Either
    -0.79
    Either
    -0.78
    either
    -0.76
     moreover
    -0.75
     malah
    -0.73
     además
    -0.72
     instead
    -0.71
     even
    -0.71
     invece
    -0.70
    POSITIVE LOGITS
     technically
    1.28
     initially
    1.18
     nominally
    1.16
     inicialmente
    1.01
     admittedly
    1.01
    Initially
    0.99
     ostensibly
    0.99
     theoretically
    0.98
     Initially
    0.98
     Technically
    0.97
    Activations Density 0.761%

    No Known Activations