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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 31102
    Prev
    Next
    INDEX
    Explanations

    instances of the dollar sign symbol, indicating references to monetary values or currency

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

    request result status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __":
    -0.90
    UnusedPrivate
    -0.82
    __':
    -0.81
    ?")
    -0.77
     betweenstory
    -0.74
    fromnode
    -0.73
    XmlType
    -0.70
    paravant
    -0.68
    ']")
    -0.68
    __":
    -0.67
    POSITIVE LOGITS
     moelle
    0.55
     [];
    0.54
    Succeeded
    0.52
    ;
    0.51
     McP
    0.50
    responseBody
    0.50
    bigliamento
    0.49
     =
    0.49
    vención
    0.49
     Diseño
    0.48
    Activations Density 0.009%

    No Known Activations