© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1285
    Prev
    Next
    INDEX
    Explanations

    phrases indicating integration and connection among different components or entities

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

    terms related to digital content management and social connectivity features

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

    converters="

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    setupUi
    -0.61
    resizingMask
    -0.60
    })`
    -0.56
    UnusedPrivate
    -0.55
    makeText
    -0.55
    +#+
    -0.53
    IndentedString
    -0.53
    تقاوى
    -0.52
    CrossRef
    -0.52
     cặp
    -0.52
    POSITIVE LOGITS
     centralized
    0.74
     together
    0.65
     Convenient
    0.65
     conveniently
    0.65
     centralised
    0.63
     roof
    0.62
    Convenient
    0.61
     convenient
    0.61
     central
    0.60
     accessible
    0.60
    Activations Density 0.063%

    No Known Activations