© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12660
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate understanding or actions related to purpose and abilities

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

    End of sentences

    np_acts-logits-general · gemini-2.0-flash

    planning and digital advertising

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.53
    paravant
    -0.52
    ViewFeatures
    -0.52
    sizeCache
    -0.49
    RTGC
    -0.48
     OkHttpClient
    -0.47
     EconPapers
    -0.46
    GEBURTSDATUM
    -0.46
     дописавши
    -0.45
    yntaxException
    -0.45
    POSITIVE LOGITS
    таратура
    0.33
    endforeach
    0.32
     couche
    0.32
    addGap
    0.32
     Reverso
    0.31
     reasonable
    0.31
    Kjelder
    0.30
     dieux
    0.30
     reasonably
    0.30
     समीक्षक
    0.30
    Activations Density 0.665%

    No Known Activations