© 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. 5451
    Prev
    Next
    INDEX
    Explanations

    the presence of specific non-alphanumeric tokens or formatting elements in the text

    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
    e
    -0.85
    ed
    -0.82
     Schroeder
    -0.81
     ORE
    -0.81
     Tind
    -0.80
    помним
    -0.78
    attro
    -0.75
    getvalue
    -0.75
     Bess
    -0.73
     Mendes
    -0.73
    POSITIVE LOGITS
    ()))
    1.60
    ']))
    1.59
    ]))
    1.50
    ())
    1.41
    ))
    1.39
    '))
    1.39
    ])
    1.38
    ++)
    1.38
    )))
    1.38
    __':
    1.37
    Activations Density 0.033%

    No Known Activations