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. 10-GEMMASCOPE-RES-16K
    6. 13322
    Prev
    Next
    INDEX
    Explanations

    technical terms related to pneumatic systems and their dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ney
    -0.69
    Ney
    -0.63
     متعلقه
    -0.62
     Normdatei
    -0.60
    hadow
    -0.60
    DebuggerNonUser
    -0.59
    dients
    -0.59
    Coder
    -0.58
    BRC
    -0.58
    rungsseite
    -0.57
    POSITIVE LOGITS
     Vibration
    0.68
     vibration
    0.65
    Vibration
    0.64
    IContainer
    0.62
     vibrations
    0.62
     springing
    0.60
     SPRING
    0.59
     Spring
    0.59
     amorti
    0.58
    ần
    0.57
    Activations Density 0.501%

    No Known Activations