© 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. 14517
    Prev
    Next
    INDEX
    Explanations

    phrases that highlight methods or manners of doing something

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

    phrases describing methods or manners of doing something, particularly the phrase pattern "in a [adjective] way."

    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
     Autorisations
    -0.34
    ธอ
    -0.28
     kendisi
    -0.26
    zionata
    -0.26
     useAppContext
    -0.25
    šinou
    -0.25
     unbedingt
    -0.25
     зрения
    -0.25
    toPromise
    -0.25
    VolleyError
    -0.25
    POSITIVE LOGITS
     ways
    1.77
     way
    1.77
     manner
    1.70
    manner
    1.39
     manière
    1.30
     Ways
    1.27
     manera
    1.26
     WAYS
    1.25
     façon
    1.25
     WAY
    1.24
    Activations Density 0.382%

    No Known Activations