© 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. 2-GEMMASCOPE-RES-16K
    11. 5272
    Prev
    Next
    INDEX
    Explanations

    occurrences of certain property-related terms in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -1.02
     Meksiku
    -0.95
    Bundle
    -0.87
    UnsafeEnabled
    -0.86
     незавершена
    -0.84
     disambiguazione
    -0.84
    脚注の使い方
    -0.83
    دانشنامهٔ
    -0.82
     Wiktionnaire
    -0.81
    featureID
    -0.80
    POSITIVE LOGITS
     prop
    2.10
    prop
    1.73
     Prop
    1.69
    Prop
    1.69
     props
    1.55
    props
    1.48
     Props
    1.43
     PROP
    1.35
    Props
    1.32
    PROP
    1.22
    Activations Density 0.024%

    No Known Activations