© 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. 6325
    Prev
    Next
    INDEX
    Explanations

    discussions about the importance and role of theater in society

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

    doubt, uncertainty, or qualification

    np_acts-logits-general · gemini-2.0-flash

    qualifiers like "thing" or "sort"

    np_acts-logits-general · gemini-2.5-flash-lite

    transitional and connective phrasing that organizes discourse (contrast, cause/effect, sequencing) and adds evaluative or attitudinal tone within sentences.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    casted
    -0.80
     Zeitraum
    -0.69
    webElementXpaths
    -0.68
     detrimental
    -0.66
     damaligen
    -0.65
    IntoConstraints
    -0.65
     respective
    -0.64
    utilizzo
    -0.63
     attire
    -0.62
    InjectMocks
    -0.62
    POSITIVE LOGITS
     variously
    0.50
    reszcie
    0.50
     offenbar
    0.48
    ❦
    0.46
     särskilt
    0.45
     freilich
    0.45
     doubtless
    0.45
     («
    0.44
     daß
    0.43
    たとえば
    0.42
    Activations Density 5.864%

    No Known Activations