© 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. 21-GEMMASCOPE-RES-16K
    6. 11804
    Prev
    Next
    INDEX
    Explanations

    technical terms related to mechanical properties and testing of materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     اطلع
    -0.48
    piecze
    -0.47
    TRAILING
    -0.46
    partida
    -0.46
    institution
    -0.46
    pravy
    -0.45
     institution
    -0.45
    banden
    -0.44
    collegiate
    -0.42
     pous
    -0.42
    POSITIVE LOGITS
     volume
    1.50
    volume
    1.35
     cross
    1.27
     Volume
    1.23
     area
    1.23
    Volume
    1.21
     volumen
    1.12
     VOLUME
    1.12
     volumes
    1.10
    VOLUME
    1.10
    Activations Density 0.487%

    No Known Activations