© 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 - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 1635
    Prev
    Next
    INDEX
    Explanations

    references to mobile research and survey methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beginnetje
    -0.66
    lapsingToolbar
    -0.53
     الرياضيه
    -0.49
    PhysRevLett
    -0.49
    inherit
    -0.47
     arqu
    -0.47
    sizeCache
    -0.47
     gainera
    -0.46
    Література
    -0.46
    ksikon
    -0.46
    POSITIVE LOGITS
     survey
    2.00
     surveys
    1.76
     Survey
    1.72
    survey
    1.67
     poll
    1.66
    Survey
    1.65
     surveyed
    1.55
     Surveys
    1.54
     SURVEY
    1.51
     surveying
    1.46
    Activations Density 0.503%

    No Known Activations