© 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. 9-GEMMASCOPE-RES-131K
    11. 16808
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific programming or mathematical syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    CloseOperation
    -0.70
    UseVisualStyle
    -0.66
     AttributeSet
    -0.66
    jsxFileName
    -0.66
    Personendaten
    -0.64
    setVerticalGroup
    -0.62
    UnusedPrivate
    -0.57
     kasarigan
    -0.57
    awtextra
    -0.57
    createCanvas
    -0.57
    POSITIVE LOGITS
     OnInit
    0.61
     hadir
    0.33
     préfé
    0.33
     mukana
    0.33
     RCMP
    0.30
     verletzt
    0.30
     ๆ
    0.29
     käytt
    0.29
     riun
    0.29
     sejumlah
    0.29
    Activations Density 0.000%

    No Known Activations