© 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. 10591
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly those related to financial or mathematical contexts

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

    commas that separate clauses or list items in longer sentences.

    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
    ArrowToggle
    -0.81
    ImageContext
    -0.70
     kaarangay
    -0.69
     Савезне
    -0.66
    WireFormatLite
    -0.66
     Italijanski
    -0.66
    basicConfig
    -0.65
    RTLR
    -0.65
    ValueStyle
    -0.65
     MessageBoxIcon
    -0.62
    POSITIVE LOGITS
     there
    1.08
     we
    0.98
     it
    0.87
     they
    0.85
    there
    0.75
     you
    0.73
     فإن
    0.64
     he
    0.58
     inilah
    0.57
     she
    0.56
    Activations Density 0.732%

    No Known Activations