© 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. 16-GEMMASCOPE-RES-16K
    11. 7341
    Prev
    Next
    INDEX
    Explanations

    structural or section headers in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text section or subsection labels

    np_acts-logits-general · gemini-2.0-flash

    section labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mergeFrom
    -0.86
    contentLoaded
    -0.82
    _));
    -0.81
     CreateTagHelper
    -0.79
    TintMode
    -0.78
     ProtoMessage
    -0.73
     AspNetCore
    -0.73
    日閲覧
    -0.72
     ApiException
    -0.71
     unknownFields
    -0.70
    POSITIVE LOGITS
    tvguidetime
    0.88
    </h4>
    0.81
    </h3>
    0.68
    </h1>
    0.66
    </b>
    0.66
    </h2>
    0.60
    </h5>
    0.58
    XmlRootElement
    0.53
     חיצוניים
    0.52
    mtable
    0.50
    Activations Density 0.668%

    No Known Activations