© 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. 398
    Prev
    Next
    INDEX
    Explanations

    code structure and namespaces in programming

    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
     Paglinawan
    -0.57
     autorytatywna
    -0.54
    IUrlHelper
    -0.54
    setItems
    -0.53
     Италијани
    -0.51
    doria
    -0.51
     információk
    -0.50
    izziness
    -0.49
    canestro
    -0.49
    Oficina
    -0.48
    POSITIVE LOGITS
    include
    1.36
     include
    0.92
    Include
    0.81
     Include
    0.76
     incluir
    0.71
    incl
    0.68
     INCLUDE
    0.66
    INCLUDE
    0.62
     incl
    0.61
    inclu
    0.60
    Activations Density 0.155%

    No Known Activations