© 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. 1-GEMMASCOPE-RES-16K
    11. 6461
    Prev
    Next
    INDEX
    Explanations

    HTML header tags indicating sections or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.94
    windowFixed
    -0.90
    ThemeOverlay
    -0.81
    ніципалі
    -0.79
    хьтан
    -0.74
    leſs
    -0.74
    FunctionFlags
    -0.73
     oprot
    -0.72
     виправивши
    -0.72
    CppMethod
    -0.71
    POSITIVE LOGITS
    </h3>
    2.61
    </h5>
    2.17
    </h4>
    2.08
    </h2>
    2.08
    </h6>
    2.03
    </h1>
    1.87
    </blockquote>
    1.45
    </td>
    1.40
    </b>
    1.35
    }*/
    1.32
    Activations Density 0.010%

    No Known Activations