© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 9652
    Prev
    Next
    INDEX
    Explanations

    specific names or terms associated with repeated instances or patterns, along with mentions of confidence and references to navigating or guiding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LabelTagHelper
    -0.71
    !*\
    -0.65
     aconteceu
    -0.62
    AnchorStyles
    -0.61
    iprot
    -0.60
     <>",
    -0.60
    thâu
    -0.59
    <?
    -0.57
    ніципалі
    -0.57
    WarningLevel
    -0.57
    POSITIVE LOGITS
    heet
    0.78
    Repeated
    0.66
     betweenstory
    0.65
    complexType
    0.64
     charset
    0.63
     Fern
    0.63
    جغرافيا
    0.62
    heets
    0.61
     nons
    0.58
    جة
    0.58
    Activations Density 0.095%

    No Known Activations