© 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. 3-GEMMASCOPE-RES-16K
    6. 12688
    Prev
    Next
    INDEX
    Explanations

    mentions of rewards and concepts related to reward systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.86
    findpost
    -0.71
     متعلقه
    -0.70
     goutte
    -0.70
    CGContext
    -0.68
    مراجع
    -0.67
    mıştır
    -0.67
    pshots
    -0.66
     odkazy
    -0.65
    Tracey
    -0.64
    POSITIVE LOGITS
     reward
    1.72
     rewards
    1.67
     Reward
    1.66
     Rewards
    1.60
    Reward
    1.47
    reward
    1.46
     rewarded
    1.45
    Rewards
    1.42
    rewards
    1.24
     rewarding
    1.24
    Activations Density 0.098%

    No Known Activations