© 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. 19-GEMMASCOPE-RES-16K
    11. 11012
    Prev
    Next
    INDEX
    Explanations

    references to geographic or contextual breadth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ListNode
    -0.69
     känna
    -0.66
    HasAnnotation
    -0.64
     exclusivas
    -0.62
    hasMoreElements
    -0.61
    gameserver
    -0.61
     compagni
    -0.59
     colorear
    -0.59
     TreeNode
    -0.59
    Anhalt
    -0.58
    POSITIVE LOGITS
     across
    0.94
     ACROSS
    0.94
    across
    0.89
    Across
    0.88
     Across
    0.86
     generations
    0.73
     crossed
    0.73
     crosses
    0.72
     crossings
    0.72
     crossing
    0.72
    Activations Density 0.061%

    No Known Activations