Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 35336
    Prev
    Next
    INDEX
    Explanations

    numerical values and references to measurements, data, or statistics

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

    numeric identifiers and references

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     ſeinem
    -0.85
     wiſſen
    -0.82
     erſten
    -0.82
     ſehr
    -0.82
     geſch
    -0.81
     فريبيس
    -0.80
     geweſen
    -0.80
     beſti
    -0.80
    ſſung
    -0.79
    <unused16>
    -0.78
    POSITIVE LOGITS
     altında
    0.23
     específica
    0.22
     varones
    0.22
     jälkeen
    0.22
     efectuar
    0.22
    ab
    0.22
     selatan
    0.21
    d
    0.20
     pos
    0.20
     liksom
    0.20
    Activations Density 0.120%

    No Known Activations