© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 12578
    Prev
    Next
    INDEX
    Explanations

    references to healing and resource management in a gaming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 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
     Gegend
    -0.44
     Vergangenheit
    -0.41
     BIBSYS
    -0.41
     męski
    -0.40
     nė
    -0.40
     Italij
    -0.39
     Umgebung
    -0.39
     Nachfolger
    -0.39
     omgeving
    -0.39
     zengin
    -0.38
    POSITIVE LOGITS
     HP
    0.59
    AttributeSet
    0.59
     hp
    0.56
    HP
    0.56
    hp
    0.52
     &___
    0.52
     Hp
    0.51
    исленность
    0.50
    SequentialGroup
    0.50
    ThroughAttribute
    0.48
    Activations Density 0.131%

    No Known Activations