© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 31702
    Prev
    Next
    INDEX
    Explanations

    references to support resources or assistance services

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    crisis hotlines and helplines

    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
    Negative Logits
     متعلقه
    -0.70
    PerformLayout
    -0.69
    enderror
    -0.65
     CURIAM
    -0.61
    InputBorder
    -0.60
    IUrlHelper
    -0.58
    MessageOf
    -0.57
    locks
    -0.57
     Opa
    -0.57
    addCriterion
    -0.56
    POSITIVE LOGITS
     hotline
    0.63
     Crisis
    0.59
     financières
    0.57
     helpline
    0.56
     crisis
    0.56
     numéros
    0.55
     toll
    0.55
    Crisis
    0.54
     resources
    0.53
     fund
    0.50
    Activations Density 0.044%

    No Known Activations