© 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. 25-GEMMASCOPE-RES-16K
    6. 10774
    Prev
    Next
    INDEX
    Explanations

    references to programming, particularly in relation to coding logic and variable management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yourself
    -0.61
    yourself
    -0.58
     Yourself
    -0.58
     yourselves
    -0.55
    Yourself
    -0.55
     YOURSELF
    -0.51
     rospy
    -0.49
     myself
    -0.47
    ----</
    -0.47
    roring
    -0.46
    POSITIVE LOGITS
    volves
    0.78
     Does
    0.70
    Does
    0.70
    Adds
    0.67
    Requires
    0.60
    ází
    0.58
    uje
    0.57
    ει
    0.57
     Requires
    0.56
    вет
    0.56
    Activations Density 0.059%

    No Known Activations