© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 7113
    Prev
    Next
    INDEX
    Explanations

    various forms of closing punctuation or bracket characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ing
    -0.85
     Tof
    -0.80
     Loth
    -0.76
     fact
    -0.75
     Altos
    -0.72
    ̯
    -0.70
     Ribs
    -0.70
     Dawes
    -0.70
     Elmo
    -0.69
    帖最后由
    -0.69
    POSITIVE LOGITS
    ))
    1.18
    ]))
    0.99
    ()))
    0.99
    ]]
    0.96
    __))
    0.94
    )),
    0.91
    ]],
    0.89
    SPJ
    0.89
    )));
    0.88
     ))
    0.88
    Activations Density 0.391%

    No Known Activations