© 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. 4-GEMMASCOPE-RES-16K
    11. 3722
    Prev
    Next
    INDEX
    Explanations

    instances of the word "listen" or its variations, indicating a focus on active listening

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    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
    -0.97
    DotNetBar
    -0.83
     piú
    -0.82
    AlterField
    -0.81
     MainAxisSize
    -0.80
    posedge
    -0.79
     defraud
    -0.79
    rungsseite
    -0.78
     الرياضيه
    -0.78
    BufferException
    -0.76
    POSITIVE LOGITS
     listen
    2.59
     listening
    2.47
     Listen
    2.39
     listens
    2.38
     listened
    2.31
     LISTEN
    2.30
    Listen
    2.24
     Listening
    2.22
    listen
    2.07
    Listening
    2.02
    Activations Density 0.036%

    No Known Activations