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. 1063
    Prev
    Next
    INDEX
    Explanations

    references to types of aircraft or planes

    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
    EDEFAULT
    -0.76
     jeunesse
    -0.69
    NameInMap
    -0.66
    Према
    -0.65
    处的
    -0.64
    iomanip
    -0.63
     Cummings
    -0.62
     sumpay
    -0.62
    ormick
    -0.61
    rungsseite
    -0.61
    POSITIVE LOGITS
     plane
    3.17
     Plane
    2.95
     planes
    2.91
    plane
    2.90
     PLANE
    2.82
    Plane
    2.77
    planes
    2.68
     Planes
    2.51
    PLANE
    2.50
    Planes
    2.36
    Activations Density 0.043%

    No Known Activations