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. 10112
    Prev
    Next
    INDEX
    Explanations

    instances of the word "sole," indicating singularity or exclusivity

    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
    ****************
    -0.68
     prefi
    -0.63
     Huguen
    -0.62
     Monfieur
    -0.61
     Parigi
    -0.61
    قبال
    -0.60
     ---------------
    -0.60
    czo
    -0.59
     talkin
    -0.57
     centa
    -0.55
    POSITIVE LOGITS
     sole
    2.35
     Sole
    2.33
    Sole
    2.32
    sole
    2.08
     SOLE
    1.94
    SOLE
    1.55
     soles
    1.42
     solely
    1.12
    oles
    0.94
     lone
    0.88
    Activations Density 0.079%

    No Known Activations