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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 1360
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the success or failure of events or plans

    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
     getItemCount
    -0.49
     poussière
    -0.47
    bayan
    -0.47
     мода
    -0.47
     volume
    -0.46
     coût
    -0.46
    ieteur
    -0.46
     option
    -0.45
     TimeUnit
    -0.45
    uxxxx
    -0.45
    POSITIVE LOGITS
     smoothly
    0.83
     smooth
    0.78
    顺利
    0.78
     EconPapers
    0.76
     utafitiHapana
    0.73
     satisfactory
    0.72
    idł
    0.71
     saites
    0.71
    smooth
    0.67
     smoothness
    0.65
    Activations Density 0.366%

    No Known Activations