© 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. 2-GEMMASCOPE-RES-16K
    11. 8886
    Prev
    Next
    INDEX
    Explanations

    structured lists and references to actual occurrences or original concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    étant
    -0.47
     being
    -0.46
     ře
    -0.41
     having
    -0.41
    vailability
    -0.40
     nór
    -0.38
     navideña
    -0.38
    écou
    -0.38
     étant
    -0.37
     redonda
    -0.37
    POSITIVE LOGITS
     actual
    1.02
    actual
    0.96
     original
    0.88
    original
    0.86
    Actual
    0.85
     Actual
    0.84
     Original
    0.77
    ul
    0.75
     ACTUAL
    0.75
    Original
    0.74
    Activations Density 0.179%

    No Known Activations