© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 6644
    Prev
    Next
    INDEX
    Explanations

    references to motherhood and family dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     uſed
    -0.58
     ſtand
    -0.56
     RSSSF
    -0.56
     initComponents
    -0.55
    HttpPut
    -0.54
     Konami
    -0.52
    таратура
    -0.51
    kháu
    -0.50
     IService
    -0.50
     widows
    -0.49
    POSITIVE LOGITS
     little
    1.73
    little
    1.60
     baby
    1.56
    Little
    1.38
     LITTLE
    1.37
    baby
    1.30
     Little
    1.30
    LITTLE
    1.29
     Baby
    1.26
     BABY
    1.19
    Activations Density 0.160%

    No Known Activations