© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 31168
    Prev
    Next
    INDEX
    Explanations

    instances of shutdown or cessation actions

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

    shut down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CTS
    -0.40
    PKCS
    -0.35
    lccn
    -0.34
     erwarten
    -0.34
    eky
    -0.33
     PGC
    -0.32
    <!--[
    -0.32
     fit
    -0.32
     prefer
    -0.31
     Bex
    -0.31
    POSITIVE LOGITS
     shutdown
    1.31
     Shutdown
    1.27
    shutdown
    1.10
    utdown
    1.05
    Shutdown
    1.04
     shutting
    1.02
     shut
    0.96
     shuts
    0.83
     Shut
    0.81
    shut
    0.81
    Activations Density 0.005%

    No Known Activations