© 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. 0-GEMMASCOPE-RES-16K
    11. 9602
    Prev
    Next
    INDEX
    Explanations

    terms related to intermediate levels or stages in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spo
    -0.53
     pastic
    -0.49
    БО
    -0.49
     P
    -0.48
     Central
    -0.47
    timento
    -0.47
     doInBackground
    -0.47
    SPORT
    -0.46
     mad
    -0.46
    以来
    -0.46
    POSITIVE LOGITS
     auroit
    0.96
     myſelf
    0.94
     étoit
    0.90
     avoient
    0.88
     Monfieur
    0.87
     noastre
    0.87
     réaliste
    0.86
     ainfi
    0.85
     themſelves
    0.85
     exécu
    0.85
    Activations Density 0.107%

    No Known Activations