© 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. 5164
    Prev
    Next
    INDEX
    Explanations

    specific mathematical or programming syntax and formatting related to functions and algorithms

    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
    LEncoder
    -0.66
     calib
    -0.62
    roy
    -0.60
    PMailer
    -0.58
     mah
    -0.58
     ory
    -0.58
     lat
    -0.58
    ••••
    -0.57
     Lati
    -0.57
    omi
    -0.57
    POSITIVE LOGITS
    )$
    2.79
    })$
    1.95
    \}$
    1.84
    ]$
    1.81
    ))$
    1.77
    )}$
    1.74
    )$}
    1.67
    )]$
    1.64
    )$,
    1.61
    )\}$
    1.58
    Activations Density 0.201%

    No Known Activations