© 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. 2-GEMMASCOPE-RES-16K
    6. 2560
    Prev
    Next
    INDEX
    Explanations

    references to the interior of spaces, particularly in vehicles and buildings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bedaan
    -0.64
    囗
    -0.58
    良いです
    -0.55
    ướ
    -0.55
     فرق
    -0.54
    EDEFAULT
    -0.54
     cubano
    -0.54
    writeFieldEnd
    -0.54
    uç
    -0.53
     ges
    -0.52
    POSITIVE LOGITS
     interior
    1.61
     Interior
    1.57
     interiors
    1.49
    interior
    1.49
    Interior
    1.46
     INTERIOR
    1.42
    INTERIOR
    1.21
     Exterior
    1.17
     Interiors
    1.16
     exterior
    1.14
    Activations Density 0.045%

    No Known Activations