© 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. 2097
    Prev
    Next
    INDEX
    Explanations

    terms related to academic performance and evaluation

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

    words and phrases describing negative or problematic conditions and outcomes.

    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
     récents
    -0.40
    PRNewswire
    -0.38
     récentes
    -0.37
     étrangères
    -0.34
     nécessaires
    -0.34
     незавершена
    -0.33
     actuels
    -0.33
     actuelles
    -0.30
     étrangère
    -0.30
     semblables
    -0.30
    POSITIVE LOGITS
     financially
    1.81
     physically
    1.77
     academically
    1.71
     musically
    1.70
     economically
    1.68
     spiritually
    1.68
     intellectually
    1.67
     psychologically
    1.66
     politically
    1.58
     mentally
    1.52
    Activations Density 1.242%

    No Known Activations