© 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. 7943
    Prev
    Next
    INDEX
    Explanations

    instances of insistence or persistence in dialogue or narratives

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

    words and phrases expressing determination, persistence, or insistence in pursuing a goal despite obstacles or refusal.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    first-person narrative expressions of persistence, determination, or insistence in the face of obstacles or resistance.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    expressions of persistence or determination, especially insisting on continuing despite resistance or difficulty.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    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
     समीक्षाओं
    -0.46
    Glej
    -0.45
    Välislingid
    -0.44
    Notae
    -0.43
    AndEndTag
    -0.39
    Personensuche
    -0.39
     bilan
    -0.39
    
    -0.38
    valg
    -0.38
    あっという間に
    -0.38
    POSITIVE LOGITS
     persistence
    1.99
     persistent
    1.78
     persist
    1.76
     persisted
    1.73
     Persistence
    1.73
     stubborn
    1.66
     Persistent
    1.62
     persever
    1.55
     persists
    1.52
     insistent
    1.52
    Activations Density 0.412%

    No Known Activations