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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 12882
    Prev
    Next
    INDEX
    Explanations

    expressions of willingness and availability in communication

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

    Expressing happiness or willingness

    np_acts-logits-general · gemini-2.0-flash

    happy and willing to help

    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
    ########.
    -0.66
     Мексичка
    -0.56
    AddTagHelper
    -0.50
    himovic
    -0.50
     Allociné
    -0.49
     ComVisible
    -0.49
     ostavi
    -0.48
     teşekkür
    -0.48
    ↷
    -0.48
    rtype
    -0.47
    POSITIVE LOGITS
     happy
    1.60
     willing
    1.46
    happy
    1.29
     gladly
    1.20
     HAPPY
    1.19
    willing
    1.18
     Happy
    1.18
     Willing
    1.16
    Happy
    1.15
     willingness
    1.13
    Activations Density 0.158%

    No Known Activations