© 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. 3-GEMMASCOPE-RES-16K
    11. 6735
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly quotation marks and commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    leſs
    -0.70
    fleisch
    -0.60
     of
    -0.59
     freakin
    -0.59
     Tur
    -0.54
    жды
    -0.53
     frig
    -0.53
    blech
    -0.52
    ment
    -0.52
    ztály
    -0.52
    POSITIVE LOGITS
    ',
    1.79
    )',
    1.78
    ",
    1.71
    ?',
    1.69
    ]',
    1.64
    }',
    1.61
    )",
    1.59
    ,",
    1.57
    ?",
    1.54
    ,',
    1.54
    Activations Density 0.066%

    No Known Activations