© 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. 3-GEMMASCOPE-RES-16K
    11. 5798
    Prev
    Next
    INDEX
    Explanations

    various forms of action-oriented verbs in the context of making decisions and taking responsibility

    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
    alnız
    -0.59
     compete
    -0.53
    
    -0.51
     Constitucional
    -0.49
     mange
    -0.49
     refer
    -0.47
     Verfassung
    -0.46
    Datuak
    -0.46
     plana
    -0.45
     contend
    -0.44
    POSITIVE LOGITS
    Taking
    0.89
    Getting
    0.84
     Getting
    0.80
     Taking
    0.79
    Adding
    0.78
     Adding
    0.78
    getting
    0.77
    choosing
    0.77
     Having
    0.76
    Removing
    0.74
    Activations Density 0.553%

    No Known Activations