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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 31394
    Prev
    Next
    INDEX
    Explanations

    punctuation and visual breaks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    end of phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FontWeight
    -0.81
    קישורים
    -0.79
    NUMX
    -0.75
     FetchType
    -0.73
     eslint
    -0.71
     useAuth
    -0.66
    出版年
    -0.66
     JTable
    -0.66
     HttpServlet
    -0.66
     BorderRadius
    -0.64
    POSITIVE LOGITS
    ↵↵
    1.73
    <eos>
    1.30
    ↵
    1.19
    ))).
    1.05
    }}.
    1.05
    ))$.
    1.04
    )}.
    1.03
    }.
    1.01
    ])).
    1.01
    }$.
    0.98
    Activations Density 2.417%

    No Known Activations