© 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. 10662
    Prev
    Next
    INDEX
    Explanations

    colloquial expressions and conversational language

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

    non-English words, particularly from Malay and other Southeast Asian languages.

    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
     pleaſure
    -0.60
    WindowConstants
    -0.55
    fillType
    -0.53
    ByVersion
    -0.51
    Datuak
    -0.51
    rrggbb
    -0.50
     ErrInvalid
    -0.47
     newName
    -0.47
    mnop
    -0.46
    Xna
    -0.45
    POSITIVE LOGITS
     have
    0.49
     never
    0.46
     being
    0.46
     EconPapers
    0.46
     having
    0.45
     nigdy
    0.44
    뀜
    0.44
     pernah
    0.42
     fiind
    0.42
    ayant
    0.41
    Activations Density 0.006%

    No Known Activations