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. 5-GEMMASCOPE-RES-16K
    6. 3458
    Prev
    Next
    INDEX
    Explanations

    apostrophes and their variations in usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pinulongan
    -1.19
     ―――――
    -1.17
     saites
    -1.07
     المعيارى
    -1.07
     дописавши
    -1.06
     betweenstory
    -1.06
     Meksiku
    -0.99
     ་་
    -0.98
    ViewImports
    -0.97
    SceneManagement
    -0.97
    POSITIVE LOGITS
    s
    1.64
     “
    0.98
    ’
    0.94
     ‘
    0.93
    ”
    0.89
     ’
    0.80
    “
    0.80
     '
    0.77
    ‘
    0.75
    ′
    0.72
    Activations Density 0.133%

    No Known Activations