© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 12154
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "listener" and its variants within programming contexts

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

    listener in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wrong
    -0.48
     new
    -0.48
     big
    -0.44
    <bos>
    -0.44
    0
    -0.44
    \]
    -0.43
     highly
    -0.43
    :#
    -0.42
     Gow
    -0.42
     Gord
    -0.41
    POSITIVE LOGITS
    listener
    1.36
     Listener
    1.30
    Listener
    1.27
     listener
    1.23
     listeners
    1.05
    listeners
    1.03
    Listeners
    0.98
    ActionListener
    0.88
    mListener
    0.84
     LISTEN
    0.81
    Activations Density 0.003%

    No Known Activations