© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 9629
    Prev
    Next
    INDEX
    Explanations

    phrases that describe physical processes and actions involving fluids or liquids

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

    Emitting, discharging, or ejecting something

    np_acts-logits-general · gemini-2.0-flash

    release and spill

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    testens
    -0.43
    inição
    -0.42
    XmlType
    -0.41
    ⏜
    -0.41
     ProtoMessage
    -0.40
    mbggenerated
    -0.40
     beginnetje
    -0.39
    tempel
    -0.39
    çim
    -0.39
    хьтан
    -0.38
    POSITIVE LOGITS
     release
    0.84
     keluar
    0.82
    ออกมา
    0.81
     Release
    0.77
     releasing
    0.77
     released
    0.75
    releasing
    0.71
     output
    0.71
     releases
    0.70
     spilling
    0.70
    Activations Density 0.634%

    No Known Activations