© 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. 14-GEMMASCOPE-RES-16K
    11. 4377
    Prev
    Next
    INDEX
    Explanations

    references to formal agreements, legal terms, or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RectangleBorder
    -0.75
     disambiguazione
    -0.71
     MonoBehaviour
    -0.70
    ParallelGroup
    -0.68
    TagHelper
    -0.65
    ioutil
    -0.64
     Indo
    -0.63
    Indo
    -0.62
     edible
    -0.62
    Osob
    -0.62
    POSITIVE LOGITS
     istället
    0.60
    instead
    0.59
     instead
    0.58
    Instead
    0.56
     anstatt
    0.56
     maupun
    0.56
     بلکه
    0.55
     évidence
    0.54
    ťou
    0.54
     stället
    0.54
    Activations Density 1.075%

    No Known Activations