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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2-GEMMASCOPE-RES-16K
    6. 15113
    Prev
    Next
    INDEX
    Explanations

    exclamation marks and other punctuation marks, indicating strong emotions or emphasis in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Савезне
    -0.85
    GEBURTSDATUM
    -0.82
    Abitanti
    -0.80
    хьтан
    -0.75
    :]:
    -0.73
     pinulongan
    -0.71
    mybatisplus
    -0.71
     Rosenthal
    -0.70
    ArrowToggle
    -0.69
     betweenstory
    -0.69
    POSITIVE LOGITS
    '
    1.37
     '
    1.08
    .'
    0.99
    ...'
    0.94
    s
    0.91
    -'
    0.89
    "'
    0.86
    。"
    0.86
    "
    0.84
    )'
    0.84
    Activations Density 0.286%

    No Known Activations