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. 22-GEMMASCOPE-RES-16K
    6. 3520
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to music equipment and performance

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

    Yamaha Motif keyboard/rack

    np_acts-logits-general · gemini-2.0-flash

    piano and keyboard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addContainerGap
    -0.61
    Prox
    -0.60
     समीक्षाओं
    -0.59
    ングラス
    -0.58
    PackageManager
    -0.58
     SafeMath
    -0.57
     Zoological
    -0.55
    WriteAttribute
    -0.55
    Protocols
    -0.55
    RectangleBorder
    -0.54
    POSITIVE LOGITS
     piano
    1.27
     keyboard
    1.21
     Piano
    1.17
     pianos
    1.15
    piano
    1.12
    keyboard
    1.05
     Keyboard
    1.05
    Piano
    1.05
     pian
    0.96
    Keyboard
    0.94
    Activations Density 0.169%

    No Known Activations