© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14631
    Prev
    Next
    INDEX
    Explanations

    references to children and children's hospitals

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

    "children" or related terms

    np_acts-logits-general · gemini-2.0-flash

    children's activities and contexts

    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
    •Steering experiments: Gemma 2-2B / 10-GEMMASCOPE-RES-16K

    No Comments

    Negative Logits
    WriteTagHelper
    -1.06
     TimeUnit
    -0.81
    EDEFAULT
    -0.80
    ConstraintMaker
    -0.73
    ScopeManager
    -0.72
     חיצוניים
    -0.72
     שוליים
    -0.71
    Personendaten
    -0.71
    AndEndTag
    -0.71
     ivelany
    -0.70
    POSITIVE LOGITS
    rens
    0.76
     children
    0.71
    hood
    0.70
     Children
    0.68
    Children
    0.65
     prodigy
    0.61
    children
    0.61
    ren
    0.56
     CHILDREN
    0.56
     ages
    0.55
    Activations Density 0.080%

    No Known Activations