© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 1534
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "had" and its variations in context

    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
    Had
    -0.68
     Had
    -0.64
    Искәрмәләр
    -0.61
    DebuggerNonUser
    -0.59
    had
    -0.58
     maintenant
    -0.55
    multer
    -0.54
    ValueStyle
    -0.53
    roslav
    -0.53
     actualidad
    -0.53
    POSITIVE LOGITS
     hoped
    1.32
     originally
    1.23
     earlier
    1.06
     previously
    1.05
     intended
    1.02
     initially
    1.00
     planned
    1.00
     ursprünglich
    0.94
     expected
    0.88
    s
    0.87
    Activations Density 0.150%

    No Known Activations