Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 12426
    Prev
    Next
    INDEX
    Explanations

    references to specific Linux distributions and related software installations

    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
     jsPsych
    -0.65
    PerformLayout
    -0.63
    elemField
    -0.55
     peptides
    -0.54
     gynhyrchwyd
    -0.54
    InjectAttribute
    -0.54
    abank
    -0.53
     parker
    -0.52
    LEncoder
    -0.52
    XMLSchema
    -0.52
    POSITIVE LOGITS
     Debian
    0.85
     Ubuntu
    0.82
     distro
    0.75
    Ubuntu
    0.73
     ubuntu
    0.72
     Fedora
    0.70
     deb
    0.70
    Debian
    0.70
     KDE
    0.69
     Linux
    0.67
    Activations Density 0.920%

    No Known Activations