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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 9850
    Prev
    Next
    INDEX
    Explanations

    phrases related to priorities and importance, particularly in a customer service context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after "top" or related to "priority"

    np_acts-logits-general · gemini-2.0-flash

    top priority

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OCCURRED
    -0.38
     invitamos
    -0.35
     дъ
    -0.32
     Tal
    -0.31
    ěte
    -0.31
    RTCF
    -0.31
    блу
    -0.30
    رشف
    -0.30
     soeur
    -0.30
    bibfield
    -0.30
    POSITIVE LOGITS
     priority
    2.84
     priorities
    2.52
     Priority
    2.47
    priority
    2.45
    Priority
    2.31
     prioritized
    2.30
     prioritize
    2.27
     Priorities
    2.25
     prioridad
    2.23
     prioriti
    2.22
    Activations Density 0.280%

    No Known Activations