© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8308
    Prev
    Next
    INDEX
    Explanations

    references to artificial intelligence and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -0.77
     betweenstory
    -0.63
     kap
    -0.62
     INSTR
    -0.61
     Krak
    -0.59
     omb
    -0.58
    routeProvider
    -0.58
    cruz
    -0.56
    icza
    -0.56
     Jacob
    -0.54
    POSITIVE LOGITS
     AI
    2.87
    AI
    2.48
     ai
    1.89
     Artificial
    1.74
     Ai
    1.74
    ai
    1.65
    Ai
    1.64
    Artificial
    1.58
     artificial
    1.56
    artificial
    1.53
    Activations Density 0.062%

    No Known Activations