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. 4-GEMMASCOPE-RES-16K
    6. 3485
    Prev
    Next
    INDEX
    Explanations

    data entries and structures related to processes and updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ianum
    -0.43
     Inc
    -0.42
     New
    -0.42
     Mr
    -0.40
    Explanation
    -0.39
    贯
    -0.39
    언
    -0.39
     I
    -0.39
    om
    -0.38
    巨
    -0.38
    POSITIVE LOGITS
     Wiktionnaire
    0.91
     MainAxisSize
    0.89
     متعلقه
    0.88
    Tembelea
    0.86
    fjspx
    0.82
    SpringRunner
    0.81
    balleur
    0.80
     fieldNum
    0.79
    elemField
    0.78
     تضيفلها
    0.76
    Activations Density 0.629%

    No Known Activations