© 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. 36-GEMMASCOPE-RES-16K
    11. 7833
    Prev
    Next
    INDEX
    Explanations

    phrases related to control and authority transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    一场
    -0.26
    GHIJKLM
    -0.26
    fährt
    -0.26
     faltar
    -0.24
     tutt
    -0.24
    ђу
    -0.23
    -0.23
     kalangan
    -0.23
    lesson
    -0.22
    confirmButton
    -0.22
    POSITIVE LOGITS
     control
    1.92
     ownership
    1.61
    control
    1.55
     responsibility
    1.46
     custody
    1.45
     contrôle
    1.41
     controle
    1.38
     Kontrolle
    1.36
    ownership
    1.36
     controllo
    1.36
    Activations Density 0.779%

    No Known Activations