© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 6421
    Prev
    Next
    INDEX
    Explanations

    adverbs indicating frequency or certainty

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

    the adverb "typically" across various technical and academic contexts.

    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
    AsUp
    -0.71
     autorytatywna
    -0.69
     finalement
    -0.64
     BorderSide
    -0.62
     createSprite
    -0.62
    parsedMessage
    -0.60
     '\\;'
    -0.60
    ついに
    -0.58
    multer
    -0.57
     faktisk
    -0.57
    POSITIVE LOGITS
    y
    0.57
    ً
    0.49
     hablando
    0.47
    ALLY
    0.46
     speaking
    0.46
    ally
    0.46
    적으로
    0.45
     parlant
    0.43
     falando
    0.42
    mente
    0.41
    Activations Density 0.521%

    No Known Activations