© 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. 5661
    Prev
    Next
    INDEX
    Explanations

    greetings and salutation phrases

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

    Greetings ("Hello", "Hi", "morning", "Hey")

    np_acts-logits-general · gemini-2.0-flash

    greeting followed by addressing everyone

    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
    ArgsConstructor
    -0.59
     vettoriale
    -0.57
    thenia
    -0.55
    LLocation
    -0.53
     saiba
    -0.52
     aDecoder
    -0.51
     Expédié
    -0.51
     <=>
    -0.50
    VIAF
    -0.48
     waaronder
    -0.48
    POSITIVE LOGITS
     everyone
    1.32
     everybody
    1.16
     Everyone
    1.12
     guys
    1.09
    everyone
    1.06
    Everyone
    1.01
    everybody
    0.91
     Everybody
    0.89
    Everybody
    0.88
     folks
    0.88
    Activations Density 0.076%

    No Known Activations