© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9-GEMMASCOPE-RES-131K
    11. 83840
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "the" and its linguistic derivatives

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

    quotation marks and common words

    np_acts-logits-general · gemini-2.5-flash-lite

    the neuron detects numeric tokens and number-related pieces (digits, years, ordinals, and other numeric fragments).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0

    The neuron detects numeric tokens and number-related fragments (digits, numerals, ordinals, and similar numeric parts).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     uñas
    -0.37
     Constitución
    -0.36
     Económica
    -0.31
     peligros
    -0.30
     tercero
    -0.30
     navideños
    -0.30
     fijo
    -0.28
     colectiva
    -0.28
     inalámbrica
    -0.28
     certamen
    -0.27
    POSITIVE LOGITS
     EconPapers
    0.92
     kasarigan
    0.88
    windowFixed
    0.86
    OGND
    0.85
    XmlAccessorType
    0.85
     المعيارى
    0.81
     հղումներ
    0.81
    StoryboardSegue
    0.81
    WebVitals
    0.80
    AddTagHelper
    0.80
    Activations Density 0.647%

    No Known Activations