Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 12465
    Prev
    Next
    INDEX
    Explanations

    references to legal terms and formal processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by a past-tense verb "had"

    np_acts-logits-general · gemini-2.0-flash

    past progressive tense auxiliary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    contentLoaded
    -0.75
     cherchés
    -0.74
    IntoConstraints
    -0.65
    MessageTagHelper
    -0.65
     <=",
    -0.63
    potranspiration
    -0.62
    NameInMap
    -0.61
     Wiktionnaire
    -0.61
    UIControlState
    -0.60
    PONENT
    -0.59
    POSITIVE LOGITS
     had
    3.24
    had
    2.53
    Had
    2.46
     Had
    2.39
     HAD
    2.01
     hadn
    1.90
     había
    1.80
     habían
    1.74
     hatte
    1.74
     avait
    1.73
    Activations Density 0.567%

    No Known Activations