© 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. 3-GEMMASCOPE-RES-16K
    11. 5905
    Prev
    Next
    INDEX
    Explanations

    descriptors indicating strength or effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElementXpaths
    -0.66
     referenties
    -0.65
     <=",
    -0.61
    MigrationBuilder
    -0.60
    ItemLayout
    -0.57
    GraphicsUnit
    -0.56
    sidemargin
    -0.56
    انيف
    -0.55
     AspNetCore
    -0.55
    lock
    -0.54
    POSITIVE LOGITS
     powerful
    2.82
     Powerful
    2.70
    Powerful
    2.66
    powerful
    2.59
     puissant
    2.14
     puissante
    1.96
     potente
    1.93
     powerfully
    1.87
     poderosa
    1.84
     poderosos
    1.84
    Activations Density 0.045%

    No Known Activations