© 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. 16-GEMMASCOPE-RES-16K
    11. 1341
    Prev
    Next
    INDEX
    Explanations

    information related to law enforcement and criminal activities

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

    Currency or ability related to incentives

    np_acts-logits-general · gemini-2.0-flash

    can use reward

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ControllerTest
    -0.50
    Uninitialized
    -0.48
    SharedCtor
    -0.47
     test
    -0.47
    EDEFAULT
    -0.46
     OFDb
    -0.42
     Origin
    -0.42
    Origin
    -0.42
     Test
    -0.42
    ORIGIN
    -0.41
    POSITIVE LOGITS
    toppers
    0.99
     reward
    0.93
     rewards
    0.88
     Reward
    0.87
    Reward
    0.85
     Rewards
    0.83
    Rewards
    0.82
     recompensa
    0.78
     récompense
    0.75
     Stoppers
    0.75
    Activations Density 0.125%

    No Known Activations