Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2-GEMMASCOPE-RES-16K
    6. 1094
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the concept of "making" or "creating" something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    참고
    -0.71
     '\\;'
    -0.68
     linkovi
    -0.59
    ագրություններ
    -0.58
    RegressionTest
    -0.57
     odkazy
    -0.57
     ***!
    -0.55
    urgency
    -0.55
    OGND
    -0.54
     MyBatis
    -0.54
    POSITIVE LOGITS
    Makes
    1.72
     Makes
    1.64
    makes
    1.50
     makes
    1.50
     MAKES
    1.38
    hynch
    0.80
     macht
    0.77
     faz
    0.75
     hace
    0.75
     maakt
    0.75
    Activations Density 0.155%

    No Known Activations