© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 2215
    Prev
    Next
    INDEX
    Explanations

    various HTML heading tags

    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
     Dowling
    -0.71
    pflanzen
    -0.70
     Britton
    -0.67
    ”,
    -0.63
    accountId
    -0.63
    fö
    -0.62
     uniti
    -0.62
    ectomy
    -0.62
    ="+
    -0.60
    aquin
    -0.59
    POSITIVE LOGITS
    </h3>
    1.98
    </blockquote>
    1.34
    )';
    1.28
    〉
    1.19
    ';
    
    1.17
    </h5>
    1.16
    </h6>
    1.14
     ***!
    1.14
    .';
    1.13
    /';
    1.10
    Activations Density 0.074%

    No Known Activations