Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11851
    Prev
    Next
    INDEX
    Explanations

    keywords related to recognition and rewards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CppMethod
    -0.52
     архивлан
    -0.40
     confronti
    -0.40
    IContainer
    -0.37
     становника
    -0.36
    取
    -0.36
    UrlResolution
    -0.35
    PMailer
    -0.35
    skon
    -0.35
     thème
    -0.35
    POSITIVE LOGITS
     reward
    1.22
     rewards
    1.09
     rewarded
    1.07
     Reward
    0.99
    reward
    0.95
    Reward
    0.93
     Rewards
    0.91
    rewards
    0.89
    Rewards
    0.87
     rewarding
    0.82
    Activations Density 0.287%

    No Known Activations