© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 28409
    Prev
    Next
    INDEX
    Explanations

    references to immigration policies and their impact on individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    able to happen easily

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SuspendLayout
    -0.53
    protoimpl
    -0.52
     fign
    -0.50
    ணை
    -0.50
    Static
    -0.48
    TagMode
    -0.48
    requestCode
    -0.47
    izos
    -0.47
     Inscrivez
    -0.47
    try
    -0.47
    POSITIVE LOGITS
     freely
    1.18
     unchecked
    0.94
     unrestricted
    0.93
     impunity
    0.91
     bebas
    0.86
     openly
    0.86
     easy
    0.85
     libremente
    0.81
     carefree
    0.80
     librement
    0.76
    Activations Density 0.305%

    No Known Activations