© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 6460
    Prev
    Next
    INDEX
    Explanations

    the frequency of occurrence of the word "often"

    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
     Pierson
    -0.60
    brü
    -0.58
    имущества
    -0.55
     demás
    -0.53
     Valenzuela
    -0.53
     breaths
    -0.52
    Exc
    -0.52
    getContentPane
    -0.52
    ικο
    -0.52
     verso
    -0.52
    POSITIVE LOGITS
     often
    3.52
     Often
    3.11
    often
    3.06
    Often
    2.99
     spesso
    2.57
     oftentimes
    2.53
     souvent
    2.47
     sometimes
    2.39
     frequently
    2.33
     menudo
    2.30
    Activations Density 0.073%

    No Known Activations