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. 10-GEMMASCOPE-RES-16K
    6. 11076
    Prev
    Next
    INDEX
    Explanations

    questions and statements about identity and relationships among individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vold
    -0.61
     Vela
    -0.61
     mors
    -0.61
    atl
    -0.60
    ône
    -0.60
     DIM
    -0.58
     Highlands
    -0.58
     Magna
    -0.57
     Neum
    -0.56
    PLEX
    -0.56
    POSITIVE LOGITS
     whom
    1.35
     who
    1.29
     hvem
    1.27
    whom
    1.24
     Who
    1.12
    who
    1.12
    Кто
    1.08
     whoever
    1.06
    Who
    1.05
     siapa
    1.05
    Activations Density 0.122%

    No Known Activations