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

    Neuronpedia

    APICircuit 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. 21-GEMMASCOPE-RES-16K
    6. 6490
    Prev
    Next
    INDEX
    Explanations

    themes related to sacrifice and emotional struggle in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sizeCache
    -0.80
    */),
    -0.70
     ModelExpression
    -0.67
     generally
    -0.64
    $")
    -0.64
    RefNanny
    -0.63
    tvguidetime
    -0.63
    }),
    
    -0.62
    CodedInputStream
    -0.61
    dafx
    -0.60
    POSITIVE LOGITS
     betrayal
    0.73
     betrayed
    0.69
     forever
    0.67
     hatred
    0.66
     hurt
    0.65
     forgiveness
    0.65
     forgive
    0.65
    💔
    0.64
     äls
    0.64
     harming
    0.64
    Activations Density 0.485%

    No Known Activations