Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 11039
    Prev
    Next
    INDEX
    Explanations

    logical operators and mathematical symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -0.91
     itſelf
    -0.91
     faſt
    -0.82
     myſelf
    -0.81
     themſelves
    -0.80
     juſt
    -0.79
     Majefty
    -0.77
     ſeveral
    -0.76
     ſta
    -0.75
     leſs
    -0.74
    POSITIVE LOGITS
    ])),
    0.56
    })),
    0.53
     MenuView
    0.53
    +#+#
    0.52
    RegressionTest
    0.49
    )}+\
    0.48
    </th>
    0.47
    }),
    0.47
     متعلقه
    0.47
    出版年
    0.47
    Activations Density 1.248%

    No Known Activations