© 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. 7-GEMMASCOPE-RES-16K
    11. 12438
    Prev
    Next
    INDEX
    Explanations

    references to significant decisions or choices in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     V
    -0.50
     ce
    -0.50
    Usually
    -0.45
     leg
    -0.45
     Usually
    -0.45
    usually
    -0.44
     la
    -0.44
     kasarigan
    -0.43
     v
    -0.42
     E
    -0.41
    POSITIVE LOGITS
     '\\;'
    0.90
     myſelf
    0.88
     becauſe
    0.87
     Majefty
    0.87
     Monfieur
    0.86
     whoſe
    0.86
     Efq
    0.85
     Theſe
    0.83
     ―――――
    0.81
    fjspx
    0.81
    Activations Density 1.486%

    No Known Activations