© 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. 12-GEMMASCOPE-RES-16K
    11. 582
    Prev
    Next
    INDEX
    Explanations

    phrases indicating opportunities and actions to take

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jetbrains
    -0.68
     exig
    -0.62
     venait
    -0.59
     ilman
    -0.59
    Told
    -0.58
     STY
    -0.58
    一見
    -0.57
     meint
    -0.56
     alternates
    -0.56
     fuis
    -0.56
    POSITIVE LOGITS
     make
    0.98
     take
    0.90
     put
    0.83
     bring
    0.83
     share
    0.81
     keep
    0.79
     run
    0.77
     get
    0.77
     give
    0.77
     be
    0.76
    Activations Density 0.881%

    No Known Activations