© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3544
    Prev
    Next
    INDEX
    Explanations

    references to reinforcement learning techniques

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

    Markov chains, states, and state transitions

    np_acts-logits-general · gemini-2.0-flash

    state transition dynamics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Shetty
    -0.47
     Waterhouse
    -0.45
     Album
    -0.43
    غب
    -0.41
     bre
    -0.41
    麓
    -0.40
    тиво
    -0.40
     Gef
    -0.39
    atás
    -0.37
    пель
    -0.36
    POSITIVE LOGITS
     createState
    0.92
    nextState
    0.92
     state
    0.91
     states
    0.84
     newState
    0.84
     State
    0.84
     reward
    0.82
     STATE
    0.82
    state
    0.82
     currentState
    0.81
    Activations Density 0.380%

    No Known Activations