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. 77134
    Prev
    Next
    INDEX
    Explanations

    parts of documents that discuss personal opinions and experiences related to thematic or societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     CURIAM
    -0.41
     oposición
    -0.36
     manicura
    -0.35
    ]--;
    -0.34
    tedrale
    -0.33
     erity
    -0.33
     ripet
    -0.33
     insists
    -0.33
     rifi
    -0.32
     Gegenteil
    -0.32
    POSITIVE LOGITS
     betweenstory
    0.69
    +#+#
    0.66
     CallOverrides
    0.58
    tanleria
    0.56
    richTextPanel
    0.54
    تقاوى
    0.52
     Administrativna
    0.52
     виправивши
    0.51
     nakalista
    0.51
    matchCondition
    0.50
    Activations Density 0.419%

    No Known Activations