© 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. 18-GEMMASCOPE-RES-16K
    6. 11374
    Prev
    Next
    INDEX
    Explanations

    devices and inventions related to household and everyday items

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

    [Article] is an [appliance/instrument/device]

    np_acts-logits-general · gemini-2.0-flash

    devices and instruments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.84
    TintMode
    -0.82
    titleMargin
    -0.76
    CodedInputStream
    -0.73
    Personensuche
    -0.67
    ValueStyle
    -0.66
    IsMutable
    -0.65
    تفصیلات
    -0.65
    SequentialGroup
    -0.64
    windowFixed
    -0.63
    POSITIVE LOGITS
     instrument
    1.19
     tool
    1.15
     device
    1.07
     artifact
    0.95
     herramienta
    0.94
     item
    0.93
     instrumento
    0.93
    instrument
    0.93
     strumento
    0.91
     instruments
    0.90
    Activations Density 0.721%

    No Known Activations