© 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. 3-GEMMASCOPE-RES-16K
    11. 13182
    Prev
    Next
    INDEX
    Explanations

    references to various cities in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ftagPool
    -0.84
    }],
    -0.76
    })()
    -0.75
     '\\;'
    -0.70
    }]
    -0.69
    prüche
    -0.68
    ISupport
    -0.68
    icação
    -0.67
     Watanabe
    -0.66
    ]<<"
    -0.66
    POSITIVE LOGITS
     cities
    1.99
     Cities
    1.98
    Cities
    1.74
    cities
    1.66
     CITIES
    1.65
     Städte
    1.34
     Städten
    1.29
     ciudades
    1.17
     villes
    1.14
     городов
    1.09
    Activations Density 0.101%

    No Known Activations