© 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. 8428
    Prev
    Next
    INDEX
    Explanations

    phrases related to opportunities and achievements

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

    phrases expressing intention, purpose, or desired outcomes using "to" infinitive constructions.

    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
    Skocz
    -0.37
    uudet
    -0.34
    Ответить
    -0.34
     rootReducer
    -0.33
    各项
    -0.32
    mergeFrom
    -0.31
     progettazione
    -0.31
     recommandée
    -0.31
    Everyday
    -0.31
     kyllä
    -0.31
    POSITIVE LOGITS
     distraction
    0.60
     familiarize
    0.60
     sekaligus
    0.60
     fresh
    0.59
     excuse
    0.59
     continuity
    0.59
     legitimacy
    0.58
     additional
    0.57
     familiarity
    0.57
     incentive
    0.57
    Activations Density 0.591%

    No Known Activations