Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 4451
    Prev
    Next
    INDEX
    Explanations

    references to long-term relationships and commitments

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

    Relationship status or partner

    np_acts-logits-general · gemini-2.0-flash

    relationship partner union

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     épouse
    -0.74
     marrying
    -0.71
    TagMode
    -0.71
     ProtoMessage
    -0.70
    Wife
    -0.70
     Wife
    -0.69
    UIControlState
    -0.69
     виправивши
    -0.69
     suaminya
    -0.69
     bride
    -0.69
    POSITIVE LOGITS
     committed
    0.67
     flamme
    0.60
     salido
    0.60
     fling
    0.53
    committed
    0.52
     steady
    0.51
    mbggenerated
    0.50
     dal
    0.50
     serious
    0.50
     hook
    0.49
    Activations Density 0.246%

    No Known Activations