© 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. 25-GEMMASCOPE-RES-16K
    6. 4768
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "have" in various tenses

    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
    enumii
    -0.61
    UnusedPrivate
    -0.55
    锈钢
    -0.52
    euvres
    -0.52
    auw
    -0.51
    tahui
    -0.50
    WebServlet
    -0.49
    rors
    -0.47
    createConnection
    -0.47
     otu
    -0.47
    POSITIVE LOGITS
     long
    0.88
     traditionally
    0.79
     tended
    0.79
     historically
    0.79
     consistently
    0.79
     always
    0.78
     often
    0.76
     struggled
    0.74
     repeatedly
    0.73
     yet
    0.70
    Activations Density 0.278%

    No Known Activations