© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 307
    Prev
    Next
    INDEX
    Explanations

    words that describe desirability or status

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

    attributes of authority and social standing

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

    wanted, preferred, among

    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
    BeginInit
    -0.63
    出版年
    -0.57
    ])));
    -0.55
    ConverterFactory
    -0.53
    DockStyle
    -0.53
    ]));
    -0.52
    SizeMode
    -0.51
    zecz
    -0.51
     interested
    -0.51
    ungsver
    -0.49
    POSITIVE LOGITS
     among
    0.70
     wśród
    0.69
    among
    0.65
     amongst
    0.64
     doInBackground
    0.62
     среди
    0.61
     pels
    0.60
     auprès
    0.60
     لدى
    0.59
     parmi
    0.57
    Activations Density 0.053%

    No Known Activations