© 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. 10-GEMMASCOPE-RES-16K
    11. 11142
    Prev
    Next
    INDEX
    Explanations

    geographic locations or names of places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyProduct
    -0.68
    Autoritní
    -0.58
     Exactos
    -0.57
    ]")]
    -0.56
    Gastro
    -0.55
     cref
    -0.55
    MIDDLE
    -0.54
    otonin
    -0.54
    crollView
    -0.54
     appris
    -0.53
    POSITIVE LOGITS
    avut
    0.98
     Arctic
    0.95
     arctic
    0.91
     Alaska
    0.89
     reindeer
    0.88
     Fairbanks
    0.88
     Alaskan
    0.88
     alaska
    0.86
     Eskimo
    0.85
     Siberian
    0.81
    Activations Density 0.533%

    No Known Activations