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. 8123
    Prev
    Next
    INDEX
    Explanations

    references to family relationships and personal connections

    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
     husbands
    -0.75
     Husband
    -0.73
    Husband
    -0.68
     Daughter
    -0.65
     Son
    -0.63
     Spouse
    -0.63
    Son
    -0.63
    ChildIndex
    -0.61
     marido
    -0.59
     marito
    -0.58
    POSITIVE LOGITS
     mother
    0.87
     folks
    0.70
     mom
    0.66
     grandmother
    0.64
    mother
    0.61
     father
    0.59
     step
    0.58
     mum
    0.56
     grandfather
    0.55
     Aunt
    0.54
    Activations Density 0.226%

    No Known Activations