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. 25-GEMMASCOPE-RES-16K
    6. 7338
    Prev
    Next
    INDEX
    Explanations

    instances of familial and romantic relationships, particularly in the context of communication and decision-making within those relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.67
    tagHelperRunner
    -0.66
    ISupport
    -0.58
    setVerticalGroup
    -0.56
     surla
    -0.52
     disponibilités
    -0.51
    styleable
    -0.50
     snippetHide
    -0.49
    ειτουργ
    -0.48
    Únete
    -0.48
    POSITIVE LOGITS
     wife
    1.55
     spouse
    1.33
     partner
    1.21
    wife
    1.18
     husband
    1.15
     Wife
    1.08
     spouses
    1.05
     Spouse
    1.03
    Wife
    1.02
     significant
    1.00
    Activations Density 0.234%

    No Known Activations