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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 8326
    Prev
    Next
    INDEX
    Explanations

    terms related to rules, mandates, and penalties in various contexts

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

    after "rules" or punctuation marks

    np_acts-logits-general · gemini-2.0-flash

    rewards and incentives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PreferredItem
    -0.80
    ArrowToggle
    -0.77
    \{\\
    -0.55
    IntoConstraints
    -0.54
    setVerticalGroup
    -0.52
    хьтан
    -0.52
    AsUp
    -0.52
    MigrationBuilder
    -0.51
    BufferException
    -0.50
     HasFactory
    -0.48
    POSITIVE LOGITS
     rewards
    0.92
     rewarded
    0.87
     reward
    0.86
    Rewards
    0.83
     Rewards
    0.81
     Reward
    0.70
    rewards
    0.68
    Reward
    0.65
     incentives
    0.65
     penalties
    0.62
    Activations Density 0.357%

    No Known Activations