© 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. 38-GEMMASCOPE-RES-16K
    11. 8858
    Prev
    Next
    INDEX
    Explanations

    references to age and status related to children and teenagers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hija
    -0.63
    AddTagHelper
    -0.59
     filha
    -0.59
    Daughter
    -0.58
     daughter
    -0.57
     hijas
    -0.57
    daughter
    -0.56
     daughters
    -0.56
    IsMutable
    -0.56
    女儿
    -0.55
    POSITIVE LOGITS
     boy
    3.03
    boy
    2.48
     boys
    2.41
     Boy
    2.39
    Boy
    2.28
     BOY
    2.23
    boys
    2.09
    BOY
    2.06
     Boys
    2.00
    Boys
    1.98
    Activations Density 0.339%

    No Known Activations