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. 16-GEMMASCOPE-RES-16K
    6. 9137
    Prev
    Next
    INDEX
    Explanations

    text related to vehicle safety issues and recalls

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

    A condition or event results in a consequence

    np_acts-logits-general · gemini-2.0-flash

    eventually resulting in a state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Према
    -0.70
     kasarigan
    -0.65
    ślę
    -0.65
    AsUp
    -0.61
     AspNetCore
    -0.58
     Италијани
    -0.55
     تضيفلها
    -0.53
    abetes
    -0.52
    AnimationsModule
    -0.52
    PhysRev
    -0.52
    POSITIVE LOGITS
     eventually
    0.64
     Eventually
    0.62
     resulting
    0.59
    Eventually
    0.58
    eventually
    0.58
     ultimately
    0.57
    Symptoms
    0.56
     progressively
    0.55
     Ultimately
    0.54
     Presenting
    0.53
    Activations Density 0.495%

    No Known Activations