© 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. 22-GEMMASCOPE-RES-16K
    11. 6168
    Prev
    Next
    INDEX
    Explanations

    phrases related to dog training and behavior modification

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

    after articles "a" or "the"

    np_acts-logits-general · gemini-2.0-flash

    operant conditioning rewards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acamata
    -0.63
    GIVEREF
    -0.58
     spirituale
    -0.56
     autopsy
    -0.55
    quête
    -0.55
     rispar
    -0.54
    visiae
    -0.53
    olesterol
    -0.53
     Pilgri
    -0.52
    withIdentifier
    -0.52
    POSITIVE LOGITS
     reward
    1.17
     rewards
    1.08
     Reward
    0.97
    reward
    0.96
    Reward
    0.95
     rewarded
    0.94
     Rewards
    0.91
     reinforcement
    0.89
     rewarding
    0.88
     positive
    0.88
    Activations Density 0.297%

    No Known Activations