© 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-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 9623
    Prev
    Next
    INDEX
    Explanations

    instances of the word "stop" and its variations

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

    Variations of "stop"

    np_acts-logits-general · gemini-2.0-flash

    stop

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.85
     EconPapers
    -0.79
     HasFactory
    -0.79
    ]))
    
    -0.75
     doInBackground
    -0.71
    plier
    -0.71
     chi̍t
    -0.69
    DockStyle
    -0.68
    ItemBackground
    -0.67
    FieldDescriptor
    -0.66
    POSITIVE LOGITS
     Stops
    1.19
     STOP
    1.18
     stops
    1.15
     stop
    1.14
     Stop
    1.13
    Stop
    1.07
    STOP
    1.07
    stop
    1.03
    stops
    1.02
    Stops
    0.95
    Activations Density 0.122%

    No Known Activations