© 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. 15-GEMMASCOPE-RES-16K
    6. 11581
    Prev
    Next
    INDEX
    Explanations

    Java class names and attributes related to Android development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :
    -0.61
     (
    -0.58
    *
    -0.57
     “
    -0.55
     :
    -0.55
    ;
    -0.52
     B
    -0.52
     N
    -0.52
    ,
    -0.50
     all
    -0.48
    POSITIVE LOGITS
     houſe
    1.10
    GEBURTSDATUM
    0.97
    ConstraintMaker
    0.96
    httphttps
    0.95
    awtextra
    0.94
     Houſe
    0.93
     purpoſe
    0.89
     ſtate
    0.89
     Majefty
    0.85
     ſy
    0.85
    Activations Density 0.019%

    No Known Activations