© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 8969
    Prev
    Next
    INDEX
    Explanations

    punctuation, particularly parentheses and brackets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𝐝
    -0.64
     myth
    -0.61
    𝐮
    -0.60
     Gla
    -0.59
     Hamb
    -0.57
     the
    -0.56
    𝐡
    -0.55
     Chit
    -0.54
     Jop
    -0.54
    ad
    -0.54
    POSITIVE LOGITS
    })).
    1.35
    __).
    1.32
    ()).
    1.29
    ))).
    1.28
    ])).
    1.28
    expandindo
    1.27
    }`).
    1.24
    )).
    1.24
    ")).
    1.20
    ').
    1.20
    Activations Density 0.062%

    No Known Activations