© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 5921
    Prev
    Next
    INDEX
    Explanations

    terms related to exploitation and victimization, particularly in the context of children

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     passato
    -0.46
     رسیده
    -0.46
    に来
    -0.44
    uns
    -0.43
    MessageTagHelper
    -0.43
    as
    -0.42
     conseguenza
    -0.42
    arraycopy
    -0.39
     ostavi
    -0.39
    uts
    -0.39
    POSITIVE LOGITS
     conclusion
    0.85
     height
    0.85
     start
    0.78
     onset
    0.77
    conclusion
    0.75
     holidays
    0.73
     end
    0.72
     closing
    0.72
     final
    0.72
     beginning
    0.71
    Activations Density 0.371%

    No Known Activations