© 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. 11-GEMMASCOPE-RES-16K
    11. 4934
    Prev
    Next
    INDEX
    Explanations

    mentions of family relationships, particularly focusing on grandchildren and other descendants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleaſure
    -0.71
     leaſt
    -0.66
     Jefus
    -0.64
     Monfieur
    -0.63
     ſtate
    -0.62
     reaſon
    -0.62
     Majefty
    -0.61
    reactstrap
    -0.61
    utilisons
    -0.60
    principalColumn
    -0.59
    POSITIVE LOGITS
     grandchildren
    0.53
    +#+
    0.46
    PerformLayout
    0.44
    grandchildren
    0.43
    StackNavigator
    0.39
     grandkids
    0.35
    ParallelGroup
    0.35
     nieces
    0.34
    цтва
    0.33
     zd
    0.32
    Activations Density 0.086%

    No Known Activations