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. 14-GEMMASCOPE-RES-16K
    6. 4316
    Prev
    Next
    INDEX
    Explanations

    quantitative descriptors related to sample sizes and experimental conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.75
    তথ্যসূত্র
    -0.73
    parsedMessage
    -0.73
    Примечания
    -0.72
    sidemargin
    -0.66
     تضيفلها
    -0.66
    nEnter
    -0.61
    Digitized
    -0.61
     -_-
    -0.60
     Metropolitana
    -0.60
    POSITIVE LOGITS
     enough
    0.86
    IntoConstraints
    0.74
    enough
    0.70
     (>
    0.70
     (~
    0.56
     Enough
    0.56
     ($
    0.56
     $(
    0.55
    Enough
    0.54
     relative
    0.50
    Activations Density 0.618%

    No Known Activations