© 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. 40-GEMMASCOPE-RES-16K
    11. 6256
    Prev
    Next
    INDEX
    Explanations

    statements involving personal experiences and reflections on events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GOTREF
    -0.69
     poichè
    -0.68
     OFDb
    -0.67
     الرياضيه
    -0.66
     propOrder
    -0.66
    IVEREF
    -0.65
    MessageTagHelper
    -0.65
    RegressionTest
    -0.63
     ofc
    -0.63
     SwitchCompat
    -0.60
    POSITIVE LOGITS
     everybody
    0.81
     somebody
    0.75
     anybody
    0.72
    Anybody
    0.65
     Anybody
    0.64
    Everybody
    0.63
    everybody
    0.62
     Everybody
    0.61
     Somebody
    0.57
    somebody
    0.57
    Activations Density 0.424%

    No Known Activations