© 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. 20-GEMMASCOPE-RES-131K
    11. 22039
    Prev
    Next
    INDEX
    Explanations

    terms related to the modification and alteration of software or data

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

    modify or alter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     препратки
    -0.79
     ujednoznacz
    -0.73
    IntoConstraints
    -0.55
     MainAxisSize
    -0.54
    SharedCtor
    -0.54
     للمعارف
    -0.54
    Jeografia
    -0.54
     للاسماء
    -0.53
     InputDecoration
    -0.52
    makeConstraints
    -0.51
    POSITIVE LOGITS
     modifications
    0.69
     modification
    0.66
     alterations
    0.61
     modifi
    0.57
     alteration
    0.55
    modific
    0.51
     modificación
    0.50
     alté
    0.50
     modifies
    0.49
     modificaciones
    0.49
    Activations Density 0.027%

    No Known Activations