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. 5-GEMMASCOPE-RES-16K
    6. 3521
    Prev
    Next
    INDEX
    Explanations

    references to childhood and upbringing experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reſ
    -0.81
     ſta
    -0.77
     purpoſe
    -0.77
     perſon
    -0.77
     Inſ
    -0.76
     Diſ
    -0.75
     ſeveral
    -0.75
     ſame
    -0.74
     Theſe
    -0.74
     ſtand
    -0.73
    POSITIVE LOGITS
     juventud
    0.63
     youth
    0.62
     infância
    0.56
     childhood
    0.56
    Cubit
    0.55
     الحره
    0.54
     ddelweddau
    0.54
     age
    0.53
     Jugend
    0.53
     youthful
    0.52
    Activations Density 0.150%

    No Known Activations