© 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. 7704
    Prev
    Next
    INDEX
    Explanations

    references to moral beliefs and community-oriented values

    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
    WireFormatLite
    -0.73
    ंदीखरीदारी
    -0.66
    tvguidetime
    -0.64
    ViewImports
    -0.61
    ServletException
    -0.58
     jsPsych
    -0.55
    Искәрмәләр
    -0.55
     kaynağından
    -0.53
    GoogleApiClient
    -0.52
     <<<<<<<<<<<<<<
    -0.51
    POSITIVE LOGITS
     hards
    0.78
     working
    0.71
     rural
    0.67
     poverty
    0.67
     Appalach
    0.65
     small
    0.63
     poor
    0.62
     farming
    0.61
    ชน
    0.61
    SequentialGroup
    0.61
    Activations Density 0.377%

    No Known Activations