© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 121413
    Prev
    Next
    INDEX
    Explanations

    instances of the word "stopped" and its variations indicating cessation or interruption

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

    stopped and then

    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
    er
    -0.60
    bootstrapcdn
    -0.54
     uLocal
    -0.52
     MessageBoxIcon
    -0.50
    TemporalType
    -0.46
    uolo
    -0.46
     Wirt
    -0.46
    eric
    -0.45
    QMetaType
    -0.45
    SerializeField
    -0.44
    POSITIVE LOGITS
     stopped
    1.71
     Stopped
    1.54
    Stopped
    1.50
    stopped
    1.48
     stopping
    1.44
     stop
    1.44
     stopp
    1.39
     Stop
    1.38
     Stopping
    1.34
    Stop
    1.32
    Activations Density 0.009%

    No Known Activations