© 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. 1-GEMMASCOPE-RES-16K
    11. 3895
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -1.14
    Tikang
    -1.00
    PhysRev
    -0.96
    rawDesc
    -0.90
     disambiguazione
    -0.90
    featureID
    -0.89
     propOrder
    -0.86
    CppCodeGen
    -0.85
     ExecuteAsync
    -0.81
    ArrowToggle
    -0.79
    POSITIVE LOGITS
     sich
    1.22
     zich
    0.89
     się
    0.73
     себе
    0.68
     himself
    0.64
     mich
    0.64
    sich
    0.59
     им
    0.57
     которого
    0.57
     тебе
    0.57
    Activations Density 0.029%

    No Known Activations