© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 15342
    Prev
    Next
    INDEX
    Explanations

    situations involving the age and legal status of children, especially in contexts of citizenship and custody

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

    Age or time references

    np_acts-logits-general · gemini-2.0-flash

    age milestones

    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
    verwijspagina
    -0.79
     intStringLen
    -0.67
     propOrder
    -0.53
     convergence
    -0.49
     safety
    -0.49
    дожник
    -0.48
     loading
    -0.47
     peace
    -0.45
     делу
    -0.45
    Safety
    -0.45
    POSITIVE LOGITS
     turning
    1.61
     turns
    1.58
     Turning
    1.54
    Turning
    1.49
     turn
    1.46
    turns
    1.45
    turning
    1.39
     Turns
    1.39
    turn
    1.39
     celebrating
    1.38
    Activations Density 0.153%

    No Known Activations