© 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. 22-GEMMASCOPE-RES-16K
    11. 10151
    Prev
    Next
    INDEX
    Explanations

    instructions for troubleshooting or fixing technical issues

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

    Actions involving restarting or shutting down a system

    np_acts-logits-general · gemini-2.0-flash

    reset and restart system

    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
     []:
    -0.61
    Editable
    -0.59
    etragen
    -0.53
     pierced
    -0.52
     disponibilités
    -0.50
     oph
    -0.50
     phosph
    -0.49
     Phosph
    -0.49
    CFA
    -0.49
    Skal
    -0.49
    POSITIVE LOGITS
     reset
    1.51
     restart
    1.37
     resetting
    1.30
     Reset
    1.28
    reset
    1.28
     restarting
    1.22
     Restart
    1.20
    Reset
    1.20
     reboot
    1.20
     resets
    1.20
    Activations Density 0.255%

    No Known Activations