© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 11092
    Prev
    Next
    INDEX
    Explanations

    phrases indicating past states or conditions of people or things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "originally" and words describing initial or starting conditions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mittlerweile
    -0.90
     finalmente
    -0.90
    eventually
    -0.88
     eventually
    -0.87
    finally
    -0.86
     inzwischen
    -0.86
     finally
    -0.84
     obecnie
    -0.83
     currently
    -0.78
     ultimately
    -0.77
    POSITIVE LOGITS
     thought
    0.72
    thought
    0.57
     думал
    0.55
     Thought
    0.50
     THOUGHT
    0.50
     казалось
    0.50
    Thought
    0.50
     considered
    0.48
     believed
    0.47
     feared
    0.47
    Activations Density 0.538%

    No Known Activations