Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 5898
    Prev
    Next
    INDEX
    Explanations

    terms related to audio and listening activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.66
    UEZ
    -0.55
    блица
    -0.52
    eyed
    -0.50
    LookUp
    -0.48
     luce
    -0.48
     optical
    -0.48
    ніципалі
    -0.47
     maler
    -0.46
     Inspect
    -0.46
    POSITIVE LOGITS
     listeners
    1.40
     audio
    1.33
     listen
    1.33
     listener
    1.32
     listened
    1.29
     Listen
    1.28
     listening
    1.24
     Audio
    1.24
    Audio
    1.17
     hear
    1.17
    Activations Density 0.365%

    No Known Activations