© 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. 10866
    Prev
    Next
    INDEX
    Explanations

    indicators of progression and resolution in narratives

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

    the word "finally" and surrounding context about eventual outcomes or resolutions.

    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
     immediately
    -1.17
     inmediatamente
    -1.13
    immediately
    -1.08
     imediatamente
    -1.07
    Immediately
    -1.05
     Immediately
    -1.05
     instantly
    -1.04
     immediatamente
    -1.02
     immédiatement
    -0.97
     inmediata
    -0.96
    POSITIVE LOGITS
     finally
    0.61
     realization
    0.59
     realized
    0.59
     Finally
    0.57
     realisation
    0.56
     succumbed
    0.56
     realizes
    0.56
     realize
    0.56
     realizing
    0.54
     decide
    0.54
    Activations Density 0.489%

    No Known Activations