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. 3-GEMMASCOPE-RES-16K
    6. 15989
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "what" 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 @ 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
     Aze
    -0.78
     Blaze
    -0.67
    HostName
    -0.67
     Moors
    -0.66
     Azad
    -0.64
    alım
    -0.64
     Dm
    -0.64
     Brea
    -0.63
    erl
    -0.62
     reminder
    -0.61
    POSITIVE LOGITS
     what
    2.69
    what
    2.40
     WHAT
    2.24
    WHAT
    2.15
    What
    2.13
     What
    2.12
    whats
    1.41
     whats
    1.36
     hva
    1.26
     hvad
    1.20
    Activations Density 0.091%

    No Known Activations