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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 16374
    Prev
    Next
    INDEX
    Explanations

    expressions of intense emotion, particularly those related to screaming or vocal outbursts

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

    associated with expressing strong emotion

    np_acts-logits-general · gemini-2.0-flash

    loud sounds or vocalizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithIOException
    -0.47
     colspan
    -0.47
    coroutines
    -0.45
    cyc
    -0.42
     belo
    -0.41
    icordia
    -0.40
     Salvador
    -0.40
    äf
    -0.39
     ý
    -0.39
     translateY
    -0.39
    POSITIVE LOGITS
     loudest
    1.30
     loudly
    1.29
     louder
    1.28
     loud
    1.22
     aloud
    1.10
    Loud
    0.91
    PerformLayout
    0.90
    loud
    0.89
     Loud
    0.88
     głoś
    0.83
    Activations Density 0.101%

    No Known Activations