© 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. 5-GEMMASCOPE-RES-16K
    11. 805
    Prev
    Next
    INDEX
    Explanations

    instances of the word "listen" and its variations, indicating a focus on attentiveness and communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.95
     piú
    -0.84
    urlpatterns
    -0.83
    AlterField
    -0.83
     الرياضيه
    -0.81
    OCCURRED
    -0.78
     חיצוניים
    -0.77
    Jeografia
    -0.76
    ண்டும்
    -0.74
     resourceCulture
    -0.74
    POSITIVE LOGITS
     listen
    2.27
     listening
    2.04
     Listen
    2.03
     LISTEN
    1.98
     listened
    1.97
     listens
    1.95
     Listening
    1.89
    Listen
    1.88
    listen
    1.80
    Listening
    1.73
    Activations Density 0.031%

    No Known Activations