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. 2-GEMMASCOPE-RES-16K
    6. 6639
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "contain" and its variants

    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
    gridx
    -0.60
    lüğ
    -0.55
    ModelBuilder
    -0.54
    k
    -0.54
    -
    -0.52
     Orville
    -0.51
     arroz
    -0.51
    التالي
    -0.50
    kPa
    -0.48
    الإنجليزية
    -0.47
    POSITIVE LOGITS
     contain
    3.19
     Contain
    3.07
     contains
    3.00
     containing
    2.86
     Containing
    2.81
     Contains
    2.79
    contain
    2.77
     CONTAIN
    2.76
    Contain
    2.54
     contained
    2.52
    Activations Density 0.079%

    No Known Activations