© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 8403
    Prev
    Next
    INDEX
    Explanations

    specific mathematical functions and operations related to calculations and data structures

    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
    protoimpl
    -0.65
    :✨
    -0.61
    intellij
    -0.55
    rungsseite
    -0.54
    ミナル
    -0.53
    IndentedString
    -0.53
    XtraBars
    -0.53
    RegistryLite
    -0.52
    rrggbb
    -0.52
    WindowConstants
    -0.52
    POSITIVE LOGITS
     divided
    1.37
     divide
    1.30
     /
    1.29
    /(
    1.26
     /(
    1.24
    divide
    1.22
    divided
    1.12
     dividing
    1.11
     ÷
    1.09
    Divide
    1.09
    Activations Density 1.095%

    No Known Activations