© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 12953
    Prev
    Next
    INDEX
    Explanations

    the conditional and subjunctive forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gräns
    -0.52
     Cans
    -0.52
     assurent
    -0.47
     खरीदा
    -0.47
     offenbar
    -0.46
    alló
    -0.46
     identifica
    -0.45
     Ceramby
    -0.45
    rzej
    -0.45
     duquel
    -0.45
    POSITIVE LOGITS
     gdyby
    0.84
     незавершена
    0.83
     wouldn
    0.80
    SequentialGroup
    0.79
    would
    0.74
    wouldn
    0.72
     would
    0.71
    SpringRunner
    0.69
     Would
    0.68
    IntoConstraints
    0.68
    Activations Density 0.163%

    No Known Activations