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. 29269
    Prev
    Next
    INDEX
    Explanations

    phrases related to design and quality in products or services

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

    a more cost

    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
     gydy
    -0.40
    acijos
    -0.38
    ísimo
    -0.38
    aringan
    -0.34
     Selain
    -0.34
    inį
    -0.33
     Komunikasi
    -0.32
     pysty
    -0.32
     vandens
    -0.32
     mémoire
    -0.32
    POSITIVE LOGITS
    RectangleBorder
    0.70
    GraphicsUnit
    0.63
    iprot
    0.59
     $_"
    0.59
     hObject
    0.57
    SequentialGroup
    0.56
    localctx
    0.55
    󠁿
    0.55
    WithMany
    0.55
     ſelbſt
    0.55
    Activations Density 0.009%

    No Known Activations