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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 7251
    Prev
    Next
    INDEX
    Explanations

    phrases related to purposes or intentions for various activities, particularly in educational and research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "For" followed by purpose or testing

    np_acts-logits-general · gemini-2.0-flash

    for purpose or use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     verdad
    -0.53
     verdade
    -0.53
    VIATIONS
    -0.52
     adev
    -0.51
    برى
    -0.49
    .*")]
    -0.48
     rius
    -0.47
    SpringRunner
    -0.47
     sureties
    -0.47
     satunya
    -0.47
    POSITIVE LOGITS
     use
    1.29
     purposes
    1.16
    use
    0.97
    purposes
    0.95
     consumption
    0.94
     Purposes
    0.92
     purpose
    0.89
     Use
    0.87
    Use
    0.82
     consideration
    0.80
    Activations Density 0.297%

    No Known Activations