© 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. 9035
    Prev
    Next
    INDEX
    Explanations

    scientific and technical references or citations

    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
    </strong>
    -1.02
    </em>
    -0.86
    </b>
    -0.85
    </u>
    -0.79
    </h2>
    -0.75
    </code>
    -0.69
    </i>
    -0.69
    </h4>
    -0.59
     فريبيس
    -0.59
    ”
    -0.56
    POSITIVE LOGITS
    脚注の使い方
    0.83
     esternos
    0.82
     Roskov
    0.77
    ValueStyle
    0.75
    ">//
    0.69
    webElementGuid
    0.65
    انيف
    0.63
    @[+][
    0.61
    writeFieldEnd
    0.60
    Šaltiniai
    0.60
    Activations Density 1.075%

    No Known Activations