© 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. 35971
    Prev
    Next
    INDEX
    Explanations

    references to string resources, styles, and layouts in programming code

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

    android layout xml elements

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     habido
    -0.43
     négoci
    -0.36
     furent
    -0.36
    éndolo
    -0.36
     medarbe
    -0.35
     gestión
    -0.34
     adopción
    -0.34
     negociación
    -0.33
     passés
    -0.33
     cometido
    -0.32
    POSITIVE LOGITS
    styleable
    0.89
    fjspx
    0.83
     AssemblyCompany
    0.80
    setVerticalGroup
    0.74
    存于互联网档案馆
    0.71
     AssemblyTitle
    0.71
     imageNamed
    0.70
    stateProvider
    0.69
    IBOutlet
    0.65
    numerusform
    0.64
    Activations Density 0.014%

    No Known Activations