© 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-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 3940
    Prev
    Next
    INDEX
    Explanations

    relations between parental attributes and the child's ethnic and educational background

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mobileqq
    -0.40
     محفوظة
    -0.38
    EditorBrowsable
    -0.37
    NameInMap
    -0.36
     vastaan
    -0.34
    __':
    -0.34
    loem
    -0.33
    الإنجليزية
    -0.33
    <!--[
    -0.32
     republiky
    -0.32
    POSITIVE LOGITS
     parents
    3.67
     parent
    3.66
     Parent
    3.14
     Parents
    3.13
    parent
    3.09
    Parents
    3.06
    parents
    3.03
    Parent
    2.95
     parental
    2.94
     PARENT
    2.84
    Activations Density 1.255%

    No Known Activations