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. 3-GEMMASCOPE-RES-16K
    6. 16328
    Prev
    Next
    INDEX
    Explanations

    terms related to agricultural yield and production outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlAccessType
    -1.00
     المعيارى
    -0.95
    /*
    -0.73
     Stanton
    -0.71
    fortawesome
    -0.70
    DotNetBar
    -0.69
     Corcoran
    -0.67
     pant
    -0.65
    nsan
    -0.65
    册
    -0.64
    POSITIVE LOGITS
     yield
    3.28
     Yield
    3.24
    yield
    3.09
    Yield
    3.06
     yields
    3.02
     Yields
    2.93
    yields
    2.53
     yielding
    2.52
     yielded
    2.47
    yielding
    2.06
    Activations Density 0.079%

    No Known Activations