© 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. 9102
    Prev
    Next
    INDEX
    Explanations

    terms related to organizations, projects, and community initiatives

    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
    脚注の使い方
    -1.01
     BorderRadius
    -0.84
    ValueStyle
    -0.75
     Theſe
    -0.73
     awakeFromNib
    -0.68
     متعلقه
    -0.66
    FormState
    -0.66
     الحره
    -0.65
    errHandler
    -0.65
    isContained
    -0.64
    POSITIVE LOGITS
     that
    0.85
     whose
    0.75
     originally
    0.74
     widely
    0.70
     recently
    0.70
     often
    0.70
     previously
    0.68
     frequently
    0.67
     strongly
    0.66
     now
    0.65
    Activations Density 0.922%

    No Known Activations