© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 15771
    Prev
    Next
    INDEX
    Explanations

    terms related to electromagnetic properties and radio frequency technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.83
    ngrx
    -0.55
     esimer
    -0.55
     constaté
    -0.55
     avoient
    -0.52
     Vaux
    -0.49
    +:+
    -0.48
    Javadoc
    -0.47
    grà
    -0.46
     étoient
    -0.45
    POSITIVE LOGITS
    WebControls
    0.83
     GHz
    0.80
     MHz
    0.72
    GHz
    0.72
     antena
    0.71
     antenna
    0.70
     antennas
    0.69
     Antenna
    0.68
    Antenna
    0.68
    ennas
    0.64
    Activations Density 1.795%

    No Known Activations