© 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. 35036
    Prev
    Next
    INDEX
    Explanations

    references to parameters in a programming context

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

    parameter names

    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
    ChildScrollView
    -0.56
    ever
    -0.55
    ebra
    -0.51
    StructEnd
    -0.49
     üzere
    -0.48
    ego
    -0.47
     CreateTagHelper
    -0.47
    eyes
    -0.47
     '/';
    -0.47
    wakili
    -0.46
    POSITIVE LOGITS
     Param
    1.19
    param
    1.13
     param
    1.12
    Param
    1.10
    PARAM
    1.00
     PARAM
    0.98
    getParam
    0.90
     params
    0.78
    params
    0.77
     parameter
    0.77
    Activations Density 0.005%

    No Known Activations