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. 3-GEMMASCOPE-RES-16K
    6. 12386
    Prev
    Next
    INDEX
    Explanations

    instances of the word "because" indicating causal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Shand
    -0.84
     nadzieję
    -0.77
     Lockheed
    -0.72
     Kalman
    -0.71
     Henk
    -0.71
    ffilm
    -0.70
    ſelf
    -0.70
    olyte
    -0.69
    meals
    -0.68
    enneth
    -0.68
    POSITIVE LOGITS
     because
    2.26
    Because
    2.19
    because
    2.17
     Because
    2.09
     BECAUSE
    2.07
     porque
    1.84
    ECAUSE
    1.70
     perché
    1.61
    porque
    1.54
     Porque
    1.54
    Activations Density 0.099%

    No Known Activations