© 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. 21-GEMMASCOPE-RES-16K
    11. 15486
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    of
    -0.44
     Primavera
    -0.44
    OF
    -0.41
    ونده
    -0.40
     OF
    -0.39
    isOk
    -0.38
     hall
    -0.38
    基
    -0.38
     рук
    -0.37
     Audiodateien
    -0.37
    POSITIVE LOGITS
     AttributeSet
    0.73
    kháu
    0.72
    Enllaces
    0.68
     cherchés
    0.62
    umerable
    0.61
    
    0.60
     שוליים
    0.59
    parsedMessage
    0.59
    WebElementEntity
    0.58
    RetentionPolicy
    0.58
    Activations Density 0.248%

    No Known Activations