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. 1-GEMMASCOPE-RES-16K
    6. 13552
    Prev
    Next
    INDEX
    Explanations

    the term "IE" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pannt
    -0.66
     waard
    -0.61
    cheid
    -0.59
    ització
    -0.58
    chaub
    -0.57
    lence
    -0.56
    usages
    -0.55
    mappedBy
    -0.55
    agues
    -0.55
    Geplaatst
    -0.54
    POSITIVE LOGITS
    ie
    4.23
    IE
    3.07
     ie
    2.53
    ies
    2.12
     IE
    2.08
    Ie
    1.86
     Ie
    1.65
    iei
    1.54
    IES
    1.53
    ieb
    1.51
    Activations Density 0.061%

    No Known Activations