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. 14-GEMMASCOPE-RES-16K
    6. 10502
    Prev
    Next
    INDEX
    Explanations

    instances of the word "thus" and related transitional phrases indicating cause and effect

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Alton
    -0.70
     LON
    -0.69
    pee
    -0.68
     Pref
    -0.63
    Okey
    -0.60
     Pring
    -0.59
     Remo
    -0.59
    Waiting
    -0.59
     Pree
    -0.59
     Frankie
    -0.59
    POSITIVE LOGITS
     thus
    1.17
     Thus
    1.08
     propOrder
    1.07
    Thus
    1.02
     nahilalakip
    0.98
    thus
    0.97
    TintMode
    0.97
     Hence
    0.97
    Ainsi
    0.94
    Hence
    0.91
    Activations Density 0.158%

    No Known Activations