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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 53125
    Prev
    Next
    INDEX
    Explanations

    phrases that convey simplicity and ease of performing tasks

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

    positive descriptors of methods

    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
     resourceCulture
    -0.45
     zaak
    -0.40
     Италијани
    -0.39
    ValueStyle
    -0.38
     GenerationType
    -0.37
     setCurrent
    -0.37
    
    -0.36
     rara
    -0.36
    getCell
    -0.36
    webElementGuid
    -0.35
    POSITIVE LOGITS
    новништво
    0.54
    dafx
    0.50
    OGND
    0.47
     ***!
    0.45
     safe
    0.43
    /**
    0.41
     reliable
    0.41
    رشف
    0.41
    Chham
    0.41
    /*
    0.40
    Activations Density 0.103%

    No Known Activations