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. 25-GEMMASCOPE-RES-16K
    6. 7878
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "to be" in various forms

    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
    ρασ
    -0.51
    albeit
    -0.45
     counterparts
    -0.43
     albeit
    -0.42
    however
    -0.41
     tersebut
    -0.41
    beit
    -0.40
    though
    -0.40
    ventional
    -0.40
     ActionResult
    -0.40
    POSITIVE LOGITS
     pleased
    0.81
     delighted
    0.78
     resourceCulture
    0.77
     proud
    0.77
    Personensuche
    0.72
     Coming
    0.71
     فريبيس
    0.70
     <=",
    0.68
     excited
    0.68
    :✨
    0.68
    Activations Density 0.616%

    No Known Activations