© 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. 3-GEMMASCOPE-RES-16K
    11. 6455
    Prev
    Next
    INDEX
    Explanations

    phrases that include references to actions involving 'dealing with' or 'doing with' something

    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
    __*/
    -0.56
    참고
    -0.55
     exclusive
    -0.49
     الوا
    -0.48
     Objec
    -0.48
     Exclu
    -0.48
     Serv
    -0.48
     saites
    -0.47
     autorytatywna
    -0.47
     inso
    -0.46
    POSITIVE LOGITS
    Dealing
    0.84
     dealing
    0.84
     deal
    0.81
     dealt
    0.79
    deal
    0.75
     Dealing
    0.74
    dealing
    0.74
     DEAL
    0.71
     Deal
    0.68
    InvalidProtocol
    0.65
    Activations Density 0.294%

    No Known Activations