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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 123459
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate complexity or additional layers of meaning in a discussion

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

    more than

    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
     مرئيه
    -0.47
     ویکی‌پدیای
    -0.46
    !")
    
    -0.46
    hyrchwyd
    -0.44
    ismet
    -0.44
    }]
    
    -0.43
     **/
    
    -0.43
     الي
    -0.40
    ItemBackground
    -0.40
    点此举报
    -0.40
    POSITIVE LOGITS
    beyond
    0.53
    StoryboardSegue
    0.52
     deeper
    0.52
     Beyond
    0.52
     beyond
    0.52
     than
    0.49
    Beyond
    0.48
     BEYOND
    0.47
     allá
    0.46
    worse
    0.46
    Activations Density 0.032%

    No Known Activations