© 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. 6537
    Prev
    Next
    INDEX
    Explanations

    instances of the concept of "matching."

    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
     ModelExpression
    -1.05
    PerformLayout
    -0.93
     AssemblyCulture
    -0.82
     للمعارف
    -0.77
    StoreMessageInfo
    -0.75
     nakalista
    -0.73
    bunda
    -0.72
     utafitiHapana
    -0.72
    InitVars
    -0.72
    }});
    -0.70
    POSITIVE LOGITS
     matching
    1.21
     Matching
    1.11
    Matching
    1.06
    matching
    0.99
     matched
    0.88
    matched
    0.77
    行
    0.67
     passages
    0.64
    mapping
    0.61
     fitting
    0.60
    Activations Density 0.088%

    No Known Activations