© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 92734
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and measurements related to scientific contexts

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

    magnitude, velocity, latency, duration, potency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    identified
    -0.39
     informée
    -0.39
    UserScript
    -0.38
     autorytatywna
    -0.36
     provi
    -0.36
    chehen
    -0.35
    duit
    -0.35
     Showers
    -0.34
    práv
    -0.34
     Conf
    -0.34
    POSITIVE LOGITS
     intensity
    0.65
     density
    0.63
     thickness
    0.61
     width
    0.57
     AssemblyCulture
    0.56
     magnitude
    0.54
     Wikimedijinoj
    0.52
     Paglinawan
    0.52
     diameter
    0.52
     coefficient
    0.51
    Activations Density 0.049%

    No Known Activations