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. 10985
    Prev
    Next
    INDEX
    Explanations

    references to legislative bodies and their activities

    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
    styleUrls
    -0.60
     vane
    -0.59
    stums
    -0.49
    存于互联网档案馆
    -0.49
    <?
    -0.48
     arist
    -0.48
     samar
    -0.48
    Gemma
    -0.48
     Philist
    -0.47
     Girolamo
    -0.47
    POSITIVE LOGITS
     Congress
    1.91
    Congress
    1.72
     congress
    1.62
     CONGRESS
    1.58
     Parliament
    1.40
    congress
    1.39
     congressional
    1.31
     Congressional
    1.22
     parliament
    1.15
    Parliament
    1.10
    Activations Density 0.263%

    No Known Activations