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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 3566
    Prev
    Next
    INDEX
    Explanations

    references to specific literary or cinematic works and their series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BeginInit
    -0.60
    yarnpkg
    -0.56
    "]);
    
    -0.54
     kasarigan
    -0.53
    etheless
    -0.52
     صوتيه
    -0.51
     فريبيس
    -0.51
    μβρίου
    -0.51
    addWidget
    -0.50
    ISupport
    -0.50
    POSITIVE LOGITS
     series
    2.76
    series
    2.22
     Series
    2.07
     serie
    1.99
     SERIES
    1.98
    Series
    1.92
     série
    1.91
    系列
    1.88
    シリーズ
    1.77
     collection
    1.73
    Activations Density 0.617%

    No Known Activations