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. 1-GEMMASCOPE-RES-16K
    6. 7080
    Prev
    Next
    INDEX
    Explanations

    contexts related to making a living

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.58
     feminists
    -0.53
     uwagę
    -0.52
     Portman
    -0.50
     Steinberg
    -0.50
    Dax
    -0.49
     дописавши
    -0.49
     chùa
    -0.48
    četně
    -0.48
    Twas
    -0.48
    POSITIVE LOGITS
     living
    5.29
    living
    4.69
     Living
    4.55
    Living
    4.46
     LIVING
    4.21
    LIVING
    3.87
     lived
    2.83
     vivant
    2.57
     live
    2.54
     vivir
    2.49
    Activations Density 0.061%

    No Known Activations