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. 12-GEMMASCOPE-RES-16K
    6. 14643
    Prev
    Next
    INDEX
    Explanations

    references to algorithms or methods in data analysis and comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]='\
    -0.92
    ագրություններ
    -0.75
     متعلقه
    -0.75
     *++
    -0.68
     Waray
    -0.66
    riwal
    -0.65
     AssemblyTitle
    -0.61
    ✭✭
    -0.61
    setContentView
    -0.60
    BeginInit
    -0.59
    POSITIVE LOGITS
     ویکی‌پدیا
    0.68
    RetentionPolicy
    0.59
    IndexOf
    0.57
     index
    0.57
    indexOf
    0.56
     Indexing
    0.53
    索引
    0.51
    NSIndexPath
    0.51
     locate
    0.51
     índice
    0.50
    Activations Density 0.274%

    No Known Activations