© 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. 6281
    Prev
    Next
    INDEX
    Explanations

    instances of specific noun phrases and modal verbs

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

    the German word "das" (the definite article) and related German grammatical structures.

    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
     indisponible
    -0.57
    WriteBarrier
    -0.51
     चीज़ों
    -0.50
     purpoſe
    -0.50
    ⎨
    -0.49
     bună
    -0.49
     newOwner
    -0.49
    
    -0.46
     تضيفلها
    -0.45
    Hentet
    -0.45
    POSITIVE LOGITS
    statement
    0.42
    Дина
    0.42
    #
    0.39
     ferons
    0.37
    ianum
    0.36
    matching
    0.36
    jum
    0.35
    issement
    0.35
     Doing
    0.35
    entrum
    0.35
    Activations Density 0.006%

    No Known Activations